id	sid	tid	token	lemma	pos
9878	1	1	Digitization	Digitization	NNP
9878	1	2	of	of	IN
9878	1	3	Text	Text	NNP
9878	1	4	documents	document	NNS
9878	1	5	Using	use	VBG
9878	1	6	PDF	PDF	NNP
9878	1	7	/	/	,
9878	1	8	A	a	DT
9878	1	9	Yan	Yan	NNP
9878	1	10	Han	Han	NNP
9878	1	11	and	and	CC
9878	1	12	Xueheng	Xueheng	NNP
9878	1	13	Wan	Wan	NNP
9878	1	14	INFORMATION	INFORMATION	NNP
9878	1	15	TECHNOLOGY	TECHNOLOGY	NNP
9878	1	16	AND	and	CC
9878	1	17	LIBRARIES	library	NNS
9878	1	18	|	|	NNP
9878	1	19	MARCH	MARCH	NNP
9878	1	20	2018	2018	CD
9878	1	21	52	52	CD
9878	1	22	Yan	Yan	NNP
9878	1	23	Han	Han	NNP
9878	1	24	(	(	-LRB-
9878	1	25	yhan@email.arizona.edu	yhan@email.arizona.edu	NNP
9878	1	26	)	)	-RRB-
9878	1	27	is	be	VBZ
9878	1	28	Full	full	JJ
9878	1	29	Librarian	Librarian	NNP
9878	1	30	,	,	,
9878	1	31	the	the	DT
9878	1	32	University	University	NNP
9878	1	33	of	of	IN
9878	1	34	Arizona	Arizona	NNP
9878	1	35	Libraries	Libraries	NNPS
9878	1	36	,	,	,
9878	1	37	and	and	CC
9878	1	38	Xueheng	Xueheng	NNP
9878	1	39	Wan	Wan	NNP
9878	1	40	(	(	-LRB-
9878	1	41	wanxueheng@email.arizona.edu	wanxueheng@email.arizona.edu	NNP
9878	1	42	)	)	-RRB-
9878	1	43	is	be	VBZ
9878	1	44	a	a	DT
9878	1	45	student	student	NN
9878	1	46	,	,	,
9878	1	47	Department	Department	NNP
9878	1	48	of	of	IN
9878	1	49	Computer	Computer	NNP
9878	1	50	Science	Science	NNP
9878	1	51	,	,	,
9878	1	52	University	University	NNP
9878	1	53	of	of	IN
9878	1	54	Arizona	Arizona	NNP
9878	1	55	.	.	.
9878	2	1	ABSTRACT	ABSTRACT	NNP
9878	2	2	The	the	DT
9878	2	3	purpose	purpose	NN
9878	2	4	of	of	IN
9878	2	5	this	this	DT
9878	2	6	article	article	NN
9878	2	7	is	be	VBZ
9878	2	8	to	to	TO
9878	2	9	demonstrate	demonstrate	VB
9878	2	10	a	a	DT
9878	2	11	practical	practical	JJ
9878	2	12	use	use	NN
9878	2	13	case	case	NN
9878	2	14	of	of	IN
9878	2	15	PDF	PDF	NNP
9878	2	16	/	/	SYM
9878	2	17	A	A	NNP
9878	2	18	for	for	IN
9878	2	19	digitization	digitization	NN
9878	2	20	of	of	IN
9878	2	21	text	text	NN
9878	2	22	documents	document	NNS
9878	2	23	following	follow	VBG
9878	2	24	FADGI	FADGI	NNP
9878	2	25	’s	’s	POS
9878	2	26	recommendation	recommendation	NN
9878	2	27	of	of	IN
9878	2	28	using	use	VBG
9878	2	29	PDF	PDF	NNP
9878	2	30	/	/	,
9878	2	31	A	A	NNP
9878	2	32	as	as	IN
9878	2	33	a	a	DT
9878	2	34	preferred	preferred	JJ
9878	2	35	digitization	digitization	NN
9878	2	36	file	file	NN
9878	2	37	format	format	NN
9878	2	38	.	.	.
9878	3	1	The	the	DT
9878	3	2	authors	author	NNS
9878	3	3	demonstrate	demonstrate	VBP
9878	3	4	how	how	WRB
9878	3	5	to	to	TO
9878	3	6	convert	convert	VB
9878	3	7	and	and	CC
9878	3	8	combine	combine	VB
9878	3	9	TIFFs	TIFFs	NNPS
9878	3	10	with	with	IN
9878	3	11	associated	associated	JJ
9878	3	12	metadata	metadata	NN
9878	3	13	into	into	IN
9878	3	14	a	a	DT
9878	3	15	single	single	JJ
9878	3	16	PDF	PDF	NNP
9878	3	17	/	/	SYM
9878	3	18	A-2b	A-2b	NNP
9878	3	19	file	file	NN
9878	3	20	for	for	IN
9878	3	21	a	a	DT
9878	3	22	document	document	NN
9878	3	23	.	.	.
9878	4	1	Using	use	VBG
9878	4	2	real	real	JJ
9878	4	3	-	-	HYPH
9878	4	4	life	life	NN
9878	4	5	examples	example	NNS
9878	4	6	and	and	CC
9878	4	7	open	open	JJ
9878	4	8	source	source	NN
9878	4	9	software	software	NN
9878	4	10	,	,	,
9878	4	11	the	the	DT
9878	4	12	authors	author	NNS
9878	4	13	show	show	VBP
9878	4	14	readers	reader	NNS
9878	4	15	how	how	WRB
9878	4	16	to	to	TO
9878	4	17	convert	convert	VB
9878	4	18	TIFF	TIFF	NNP
9878	4	19	images	image	NNS
9878	4	20	,	,	,
9878	4	21	extract	extract	VB
9878	4	22	associated	associate	VBN
9878	4	23	metadata	metadata	NN
9878	4	24	and	and	CC
9878	4	25	International	International	NNP
9878	4	26	Color	Color	NNP
9878	4	27	Consortium	Consortium	NNP
9878	4	28	(	(	-LRB-
9878	4	29	ICC	ICC	NNP
9878	4	30	)	)	-RRB-
9878	4	31	profiles	profile	NNS
9878	4	32	,	,	,
9878	4	33	and	and	CC
9878	4	34	validate	validate	VB
9878	4	35	against	against	IN
9878	4	36	the	the	DT
9878	4	37	newly	newly	RB
9878	4	38	released	release	VBN
9878	4	39	PDF	PDF	NNP
9878	4	40	/	/	,
9878	4	41	A	a	DT
9878	4	42	validator	validator	NN
9878	4	43	.	.	.
9878	5	1	The	the	DT
9878	5	2	generated	generated	JJ
9878	5	3	PDF	PDF	NNP
9878	5	4	/	/	,
9878	5	5	A	a	DT
9878	5	6	file	file	NN
9878	5	7	is	be	VBZ
9878	5	8	a	a	DT
9878	5	9	self	self	NN
9878	5	10	-	-	HYPH
9878	5	11	contained	contain	VBN
9878	5	12	and	and	CC
9878	5	13	self	self	NN
9878	5	14	-	-	HYPH
9878	5	15	described	describe	VBN
9878	5	16	container	container	NN
9878	5	17	that	that	WDT
9878	5	18	accommodates	accommodate	VBZ
9878	5	19	all	all	PDT
9878	5	20	the	the	DT
9878	5	21	data	datum	NNS
9878	5	22	from	from	IN
9878	5	23	digitization	digitization	NN
9878	5	24	of	of	IN
9878	5	25	textual	textual	JJ
9878	5	26	materials	material	NNS
9878	5	27	,	,	,
9878	5	28	including	include	VBG
9878	5	29	page	page	NN
9878	5	30	-	-	HYPH
9878	5	31	level	level	NN
9878	5	32	metadata	metadata	NN
9878	5	33	and	and	CC
9878	5	34	ICC	icc	NN
9878	5	35	profiles	profile	NNS
9878	5	36	.	.	.
9878	6	1	Providing	provide	VBG
9878	6	2	theoretical	theoretical	JJ
9878	6	3	analysis	analysis	NN
9878	6	4	and	and	CC
9878	6	5	empirical	empirical	JJ
9878	6	6	examples	example	NNS
9878	6	7	,	,	,
9878	6	8	the	the	DT
9878	6	9	authors	author	NNS
9878	6	10	show	show	VBP
9878	6	11	that	that	IN
9878	6	12	PDF	PDF	NNP
9878	6	13	/	/	SYM
9878	6	14	A	A	NNP
9878	6	15	has	have	VBZ
9878	6	16	many	many	JJ
9878	6	17	advantages	advantage	NNS
9878	6	18	over	over	IN
9878	6	19	the	the	DT
9878	6	20	traditionally	traditionally	RB
9878	6	21	preferred	prefer	VBN
9878	6	22	file	file	NN
9878	6	23	format	format	NN
9878	6	24	,	,	,
9878	6	25	TIFF	TIFF	NNP
9878	6	26	/	/	SYM
9878	6	27	JPEG2000	JPEG2000	NNP
9878	6	28	,	,	,
9878	6	29	for	for	IN
9878	6	30	digitization	digitization	NN
9878	6	31	of	of	IN
9878	6	32	text	text	NN
9878	6	33	documents	document	NNS
9878	6	34	.	.	.
9878	7	1	BACKGROUND	BACKGROUND	NNP
9878	7	2	PDF	PDF	NNP
9878	7	3	has	have	VBZ
9878	7	4	been	be	VBN
9878	7	5	primarily	primarily	RB
9878	7	6	used	use	VBN
9878	7	7	as	as	IN
9878	7	8	a	a	DT
9878	7	9	file	file	NN
9878	7	10	delivery	delivery	NN
9878	7	11	format	format	NN
9878	7	12	across	across	IN
9878	7	13	many	many	JJ
9878	7	14	platforms	platform	NNS
9878	7	15	in	in	IN
9878	7	16	almost	almost	RB
9878	7	17	every	every	DT
9878	7	18	device	device	NN
9878	7	19	since	since	IN
9878	7	20	its	-PRON-	PRP$
9878	7	21	initial	initial	JJ
9878	7	22	release	release	NN
9878	7	23	in	in	IN
9878	7	24	1993	1993	CD
9878	7	25	.	.	.
9878	8	1	PDF	PDF	NNP
9878	8	2	/	/	SYM
9878	8	3	A	A	NNP
9878	8	4	was	be	VBD
9878	8	5	designed	design	VBN
9878	8	6	to	to	TO
9878	8	7	address	address	VB
9878	8	8	concerns	concern	NNS
9878	8	9	about	about	IN
9878	8	10	long	long	JJ
9878	8	11	-	-	HYPH
9878	8	12	term	term	NN
9878	8	13	preservation	preservation	NN
9878	8	14	of	of	IN
9878	8	15	PDF	PDF	NNP
9878	8	16	files	file	NNS
9878	8	17	,	,	,
9878	8	18	but	but	CC
9878	8	19	there	there	EX
9878	8	20	has	have	VBZ
9878	8	21	been	be	VBN
9878	8	22	little	little	JJ
9878	8	23	research	research	NN
9878	8	24	and	and	CC
9878	8	25	few	few	JJ
9878	8	26	implementations	implementation	NNS
9878	8	27	of	of	IN
9878	8	28	this	this	DT
9878	8	29	file	file	NN
9878	8	30	format	format	NN
9878	8	31	.	.	.
9878	9	1	Since	since	IN
9878	9	2	the	the	DT
9878	9	3	first	first	JJ
9878	9	4	standard	standard	NN
9878	9	5	(	(	-LRB-
9878	9	6	ISO	ISO	NNP
9878	9	7	19005	19005	CD
9878	9	8	PDF	PDF	NNP
9878	9	9	/	/	SYM
9878	9	10	A-1	A-1	NNP
9878	9	11	)	)	-RRB-
9878	9	12	,	,	,
9878	9	13	published	publish	VBN
9878	9	14	in	in	IN
9878	9	15	2005	2005	CD
9878	9	16	,	,	,
9878	9	17	some	some	DT
9878	9	18	articles	article	NNS
9878	9	19	discuss	discuss	VBP
9878	9	20	the	the	DT
9878	9	21	PDF	PDF	NNP
9878	9	22	/	/	,
9878	9	23	A	a	DT
9878	9	24	family	family	NN
9878	9	25	of	of	IN
9878	9	26	standards	standard	NNS
9878	9	27	,	,	,
9878	9	28	relevant	relevant	JJ
9878	9	29	information	information	NN
9878	9	30	,	,	,
9878	9	31	and	and	CC
9878	9	32	how	how	WRB
9878	9	33	to	to	TO
9878	9	34	implement	implement	VB
9878	9	35	PDF	PDF	NNP
9878	9	36	/	/	,
9878	9	37	A	A	NNP
9878	9	38	for	for	IN
9878	9	39	born	bear	VBN
9878	9	40	-	-	HYPH
9878	9	41	digital	digital	NNP
9878	9	42	documents.1	documents.1	CD
9878	9	43	There	there	EX
9878	9	44	is	be	VBZ
9878	9	45	growing	grow	VBG
9878	9	46	interest	interest	NN
9878	9	47	in	in	IN
9878	9	48	the	the	DT
9878	9	49	PDF	PDF	NNP
9878	9	50	and	and	CC
9878	9	51	PDF	PDF	NNP
9878	9	52	/	/	SYM
9878	9	53	A	a	DT
9878	9	54	standards	standard	NNS
9878	9	55	after	after	IN
9878	9	56	both	both	CC
9878	9	57	the	the	DT
9878	9	58	US	US	NNP
9878	9	59	Library	Library	NNP
9878	9	60	of	of	IN
9878	9	61	Congress	Congress	NNP
9878	9	62	and	and	CC
9878	9	63	the	the	DT
9878	9	64	National	National	NNP
9878	9	65	Archives	Archives	NNPS
9878	9	66	and	and	CC
9878	9	67	Records	Records	NNPS
9878	9	68	Administration	Administration	NNP
9878	9	69	(	(	-LRB-
9878	9	70	NARA	NARA	NNP
9878	9	71	)	)	-RRB-
9878	9	72	joined	join	VBD
9878	9	73	the	the	DT
9878	9	74	PDF	PDF	NNP
9878	9	75	Association	Association	NNP
9878	9	76	in	in	IN
9878	9	77	2017	2017	CD
9878	9	78	.	.	.
9878	10	1	NARA	NARA	NNP
9878	10	2	joined	join	VBD
9878	10	3	the	the	DT
9878	10	4	PDF	PDF	NNP
9878	10	5	Association	Association	NNP
9878	10	6	because	because	IN
9878	10	7	PDF	PDF	NNP
9878	10	8	files	file	NNS
9878	10	9	are	be	VBP
9878	10	10	used	use	VBN
9878	10	11	as	as	IN
9878	10	12	electronic	electronic	JJ
9878	10	13	documents	document	NNS
9878	10	14	in	in	IN
9878	10	15	every	every	DT
9878	10	16	government	government	NN
9878	10	17	and	and	CC
9878	10	18	business	business	NN
9878	10	19	agency	agency	NN
9878	10	20	.	.	.
9878	11	1	As	as	IN
9878	11	2	explained	explain	VBN
9878	11	3	in	in	IN
9878	11	4	a	a	DT
9878	11	5	blog	blog	NN
9878	11	6	post	post	NN
9878	11	7	,	,	,
9878	11	8	the	the	DT
9878	11	9	Library	Library	NNP
9878	11	10	of	of	IN
9878	11	11	Congress	Congress	NNP
9878	11	12	joined	join	VBD
9878	11	13	the	the	DT
9878	11	14	PDF	PDF	NNP
9878	11	15	Association	Association	NNP
9878	11	16	because	because	IN
9878	11	17	of	of	IN
9878	11	18	the	the	DT
9878	11	19	benefits	benefit	NNS
9878	11	20	to	to	IN
9878	11	21	libraries	library	NNS
9878	11	22	,	,	,
9878	11	23	including	include	VBG
9878	11	24	participating	participate	VBG
9878	11	25	in	in	IN
9878	11	26	developing	develop	VBG
9878	11	27	PDF	PDF	NNP
9878	11	28	standards	standard	NNS
9878	11	29	,	,	,
9878	11	30	promoting	promote	VBG
9878	11	31	best	good	JJS
9878	11	32	-	-	HYPH
9878	11	33	practice	practice	NN
9878	11	34	use	use	NN
9878	11	35	of	of	IN
9878	11	36	PDF	PDF	NNP
9878	11	37	,	,	,
9878	11	38	and	and	CC
9878	11	39	access	access	NN
9878	11	40	to	to	IN
9878	11	41	the	the	DT
9878	11	42	global	global	JJ
9878	11	43	expertise	expertise	NN
9878	11	44	in	in	IN
9878	11	45	PDF	PDF	NNP
9878	11	46	technology.2	technology.2	NNP
9878	11	47	Few	few	JJ
9878	11	48	articles	article	NNS
9878	11	49	,	,	,
9878	11	50	if	if	IN
9878	11	51	any	any	DT
9878	11	52	,	,	,
9878	11	53	have	have	VBP
9878	11	54	been	be	VBN
9878	11	55	published	publish	VBN
9878	11	56	about	about	IN
9878	11	57	using	use	VBG
9878	11	58	this	this	DT
9878	11	59	file	file	NN
9878	11	60	format	format	NN
9878	11	61	for	for	IN
9878	11	62	preservation	preservation	NN
9878	11	63	of	of	IN
9878	11	64	digitized	digitize	VBN
9878	11	65	content	content	NN
9878	11	66	.	.	.
9878	12	1	Yan	Yan	NNP
9878	12	2	Han	Han	NNP
9878	12	3	published	publish	VBD
9878	12	4	a	a	DT
9878	12	5	related	related	JJ
9878	12	6	article	article	NN
9878	12	7	in	in	IN
9878	12	8	2015	2015	CD
9878	12	9	about	about	IN
9878	12	10	theoretical	theoretical	JJ
9878	12	11	research	research	NN
9878	12	12	on	on	IN
9878	12	13	using	use	VBG
9878	12	14	PDF	PDF	NNP
9878	12	15	/	/	,
9878	12	16	A	a	NN
9878	12	17	for	for	IN
9878	12	18	text	text	NN
9878	12	19	documents.3	documents.3	NN
9878	12	20	In	in	IN
9878	12	21	this	this	DT
9878	12	22	article	article	NN
9878	12	23	,	,	,
9878	12	24	Han	Han	NNP
9878	12	25	discussed	discuss	VBD
9878	12	26	the	the	DT
9878	12	27	shortcomings	shortcoming	NNS
9878	12	28	of	of	IN
9878	12	29	the	the	DT
9878	12	30	widely	widely	RB
9878	12	31	used	use	VBN
9878	12	32	TIFF	TIFF	NNP
9878	12	33	and	and	CC
9878	12	34	JPEG2000	JPEG2000	NNP
9878	12	35	as	as	IN
9878	12	36	master	master	NN
9878	12	37	preservation	preservation	NN
9878	12	38	file	file	NN
9878	12	39	formats	format	NNS
9878	12	40	and	and	CC
9878	12	41	proposed	propose	VBD
9878	12	42	using	use	VBG
9878	12	43	the	the	DT
9878	12	44	then	then	RB
9878	12	45	-	-	HYPH
9878	12	46	emerging	emerge	VBG
9878	12	47	PDF	PDF	NNP
9878	12	48	/	/	,
9878	12	49	A	A	NNP
9878	12	50	as	as	IN
9878	12	51	the	the	DT
9878	12	52	preferred	preferred	JJ
9878	12	53	file	file	NN
9878	12	54	format	format	NN
9878	12	55	for	for	IN
9878	12	56	digitization	digitization	NN
9878	12	57	of	of	IN
9878	12	58	text	text	NN
9878	12	59	documents	document	NNS
9878	12	60	.	.	.
9878	13	1	Han	Han	NNP
9878	13	2	further	further	RB
9878	13	3	analyzed	analyze	VBD
9878	13	4	the	the	DT
9878	13	5	requirements	requirement	NNS
9878	13	6	mailto:yhan@email.arizona.edu	mailto:yhan@email.arizona.edu	NNP
9878	13	7	mailto:wanxueheng@email.arizona.edu	mailto:wanxueheng@email.arizona.edu	NNP
9878	13	8	DIGITIZATION	DIGITIZATION	NNS
9878	13	9	OF	of	IN
9878	13	10	TEXT	text	NN
9878	13	11	DOCUMENTS	documents	NN
9878	13	12	USING	USING	NNP
9878	13	13	PDF	PDF	NNP
9878	13	14	/	/	SYM
9878	13	15	A	A	NNP
9878	13	16	|	|	NNP
9878	13	17	HAN	HAN	NNP
9878	13	18	AND	and	CC
9878	13	19	WAN	WAN	NNP
9878	13	20	53	53	CD
9878	13	21	HTTPS://DOI.ORG/10.6017	HTTPS://DOI.ORG/10.6017	NNS
9878	13	22	/	/	SYM
9878	13	23	ITAL.V37I1.9878	ital.v37i1.9878	NN
9878	13	24	of	of	IN
9878	13	25	digitization	digitization	NN
9878	13	26	of	of	IN
9878	13	27	text	text	NN
9878	13	28	documents	document	NNS
9878	13	29	and	and	CC
9878	13	30	discussed	discuss	VBD
9878	13	31	the	the	DT
9878	13	32	advantages	advantage	NNS
9878	13	33	of	of	IN
9878	13	34	PDF	PDF	NNP
9878	13	35	/	/	SYM
9878	13	36	A	A	NNP
9878	13	37	over	over	IN
9878	13	38	TIFF	TIFF	NNP
9878	13	39	and	and	CC
9878	13	40	JPEG2000	JPEG2000	NNP
9878	13	41	.	.	.
9878	14	1	These	these	DT
9878	14	2	benefits	benefit	NNS
9878	14	3	include	include	VBP
9878	14	4	platform	platform	NN
9878	14	5	independence	independence	NN
9878	14	6	,	,	,
9878	14	7	smaller	small	JJR
9878	14	8	file	file	NN
9878	14	9	size	size	NN
9878	14	10	,	,	,
9878	14	11	better	well	JJR
9878	14	12	compression	compression	NN
9878	14	13	algorithms	algorithm	NNS
9878	14	14	,	,	,
9878	14	15	and	and	CC
9878	14	16	metadata	metadata	NN
9878	14	17	encoding	encode	VBG
9878	14	18	.	.	.
9878	15	1	In	in	IN
9878	15	2	addition	addition	NN
9878	15	3	,	,	,
9878	15	4	the	the	DT
9878	15	5	file	file	NN
9878	15	6	format	format	NN
9878	15	7	reduces	reduce	VBZ
9878	15	8	workload	workload	JJ
9878	15	9	and	and	CC
9878	15	10	simplifies	simplifie	NNS
9878	15	11	post-	post-	NNP
9878	15	12	digitization	digitization	NN
9878	15	13	processing	processing	NN
9878	15	14	such	such	JJ
9878	15	15	as	as	IN
9878	15	16	quality	quality	NN
9878	15	17	control	control	NN
9878	15	18	,	,	,
9878	15	19	adding	add	VBG
9878	15	20	and	and	CC
9878	15	21	updating	update	VBG
9878	15	22	missing	missing	JJ
9878	15	23	pages	page	NNS
9878	15	24	,	,	,
9878	15	25	and	and	CC
9878	15	26	creating	create	VBG
9878	15	27	new	new	JJ
9878	15	28	metadata	metadata	NN
9878	15	29	and	and	CC
9878	15	30	OCR	ocr	NN
9878	15	31	data	datum	NNS
9878	15	32	for	for	IN
9878	15	33	discovery	discovery	NN
9878	15	34	and	and	CC
9878	15	35	digital	digital	JJ
9878	15	36	preservation	preservation	NN
9878	15	37	.	.	.
9878	16	1	As	as	IN
9878	16	2	a	a	DT
9878	16	3	result	result	NN
9878	16	4	,	,	,
9878	16	5	PDF	PDF	NNP
9878	16	6	/	/	SYM
9878	16	7	A	a	DT
9878	16	8	can	can	MD
9878	16	9	be	be	VB
9878	16	10	used	use	VBN
9878	16	11	in	in	IN
9878	16	12	every	every	DT
9878	16	13	phase	phase	NN
9878	16	14	of	of	IN
9878	16	15	a	a	DT
9878	16	16	digital	digital	JJ
9878	16	17	object	object	NN
9878	16	18	in	in	IN
9878	16	19	an	an	DT
9878	16	20	Open	open	JJ
9878	16	21	Archival	Archival	NNP
9878	16	22	Information	Information	NNP
9878	16	23	System	System	NNP
9878	16	24	(	(	-LRB-
9878	16	25	OAIS)—for	OAIS)—for	NNP
9878	16	26	example	example	NN
9878	16	27	,	,	,
9878	16	28	a	a	DT
9878	16	29	Submission	Submission	NNP
9878	16	30	Information	Information	NNP
9878	16	31	Package	Package	NNP
9878	16	32	(	(	-LRB-
9878	16	33	SIP	SIP	NNP
9878	16	34	)	)	-RRB-
9878	16	35	,	,	,
9878	16	36	Archive	Archive	NNP
9878	16	37	Information	Information	NNP
9878	16	38	Package	Package	NNP
9878	16	39	(	(	-LRB-
9878	16	40	AIP	AIP	NNP
9878	16	41	)	)	-RRB-
9878	16	42	,	,	,
9878	16	43	and	and	CC
9878	16	44	Dissemination	Dissemination	NNP
9878	16	45	Information	Information	NNP
9878	16	46	Package	Package	NNP
9878	16	47	(	(	-LRB-
9878	16	48	DIP	DIP	NNP
9878	16	49	)	)	-RRB-
9878	16	50	.	.	.
9878	17	1	In	in	IN
9878	17	2	summary	summary	NN
9878	17	3	,	,	,
9878	17	4	a	a	DT
9878	17	5	PDF	PDF	NNP
9878	17	6	/	/	SYM
9878	17	7	A	a	DT
9878	17	8	file	file	NN
9878	17	9	can	can	MD
9878	17	10	be	be	VB
9878	17	11	a	a	DT
9878	17	12	structured	structured	JJ
9878	17	13	,	,	,
9878	17	14	self	self	NN
9878	17	15	-	-	HYPH
9878	17	16	contained	contain	VBN
9878	17	17	,	,	,
9878	17	18	and	and	CC
9878	17	19	self-	self-	NNP
9878	17	20	described	describe	VBN
9878	17	21	container	container	NNP
9878	17	22	allowing	allow	VBG
9878	17	23	a	a	DT
9878	17	24	simpler	simple	JJR
9878	17	25	one	one	CD
9878	17	26	-	-	HYPH
9878	17	27	to	to	IN
9878	17	28	-	-	HYPH
9878	17	29	one	one	CD
9878	17	30	relationship	relationship	NN
9878	17	31	between	between	IN
9878	17	32	an	an	DT
9878	17	33	original	original	JJ
9878	17	34	physical	physical	JJ
9878	17	35	document	document	NN
9878	17	36	and	and	CC
9878	17	37	its	-PRON-	PRP$
9878	17	38	digital	digital	JJ
9878	17	39	surrogate	surrogate	NN
9878	17	40	.	.	.
9878	18	1	In	in	IN
9878	18	2	September	September	NNP
9878	18	3	2016	2016	CD
9878	18	4	,	,	,
9878	18	5	the	the	DT
9878	18	6	Federal	Federal	NNP
9878	18	7	Agencies	Agencies	NNPS
9878	18	8	Digital	Digital	NNP
9878	18	9	Guidelines	Guidelines	NNP
9878	18	10	Initiative	Initiative	NNP
9878	18	11	(	(	-LRB-
9878	18	12	FADGI	FADGI	NNP
9878	18	13	)	)	-RRB-
9878	18	14	released	release	VBD
9878	18	15	its	-PRON-	PRP$
9878	18	16	latest	late	JJS
9878	18	17	guidelines	guideline	NNS
9878	18	18	for	for	IN
9878	18	19	digitization	digitization	NN
9878	18	20	related	relate	VBN
9878	18	21	to	to	IN
9878	18	22	raster	raster	NN
9878	18	23	images	image	NNS
9878	18	24	:	:	:
9878	18	25	Technical	Technical	NNP
9878	18	26	Guidelines	Guidelines	NNPS
9878	18	27	for	for	IN
9878	18	28	Digitizing	Digitizing	NNP
9878	18	29	Heritage	Heritage	NNP
9878	18	30	Materials.4	Materials.4	NNP
9878	18	31	The	the	DT
9878	18	32	de	de	JJ
9878	18	33	-	-	JJ
9878	18	34	facto	facto	VB
9878	18	35	best	good	JJS
9878	18	36	practices	practice	NNS
9878	18	37	for	for	IN
9878	18	38	digitization	digitization	NN
9878	18	39	,	,	,
9878	18	40	these	these	DT
9878	18	41	guidelines	guideline	NNS
9878	18	42	provide	provide	VBP
9878	18	43	federal	federal	JJ
9878	18	44	agencies	agency	NNS
9878	18	45	guidance	guidance	NN
9878	18	46	and	and	CC
9878	18	47	have	have	VBP
9878	18	48	been	be	VBN
9878	18	49	used	use	VBN
9878	18	50	in	in	IN
9878	18	51	many	many	JJ
9878	18	52	cultural	cultural	JJ
9878	18	53	heritage	heritage	NN
9878	18	54	institutions	institution	NNS
9878	18	55	.	.	.
9878	19	1	Both	both	DT
9878	19	2	the	the	DT
9878	19	3	PDF	PDF	NNP
9878	19	4	Association	Association	NNP
9878	19	5	and	and	CC
9878	19	6	the	the	DT
9878	19	7	authors	author	NNS
9878	19	8	welcomed	welcome	VBD
9878	19	9	the	the	DT
9878	19	10	recognition	recognition	NN
9878	19	11	of	of	IN
9878	19	12	PDF	PDF	NNP
9878	19	13	/	/	,
9878	19	14	A	A	NNP
9878	19	15	as	as	IN
9878	19	16	the	the	DT
9878	19	17	preferred	preferred	JJ
9878	19	18	master	master	NN
9878	19	19	file	file	NN
9878	19	20	format	format	NN
9878	19	21	for	for	IN
9878	19	22	digitization	digitization	NN
9878	19	23	of	of	IN
9878	19	24	text	text	NN
9878	19	25	documents	document	NNS
9878	19	26	such	such	JJ
9878	19	27	as	as	IN
9878	19	28	unbound	unbound	JJ
9878	19	29	documents	document	NNS
9878	19	30	,	,	,
9878	19	31	bound	bind	VBN
9878	19	32	volumes	volume	NNS
9878	19	33	,	,	,
9878	19	34	and	and	CC
9878	19	35	newspapers.5	newspapers.5	CD
9878	19	36	GOALS	goal	NNS
9878	19	37	AND	and	CC
9878	19	38	TASKS	task	NNS
9878	19	39	Since	since	IN
9878	19	40	Han	Han	NNP
9878	19	41	has	have	VBZ
9878	19	42	previously	previously	RB
9878	19	43	provided	provide	VBN
9878	19	44	theoretical	theoretical	JJ
9878	19	45	methods	method	NNS
9878	19	46	of	of	IN
9878	19	47	coding	code	VBG
9878	19	48	raster	raster	NN
9878	19	49	images	image	NNS
9878	19	50	,	,	,
9878	19	51	metadata	metadata	NN
9878	19	52	,	,	,
9878	19	53	and	and	CC
9878	19	54	related	related	JJ
9878	19	55	information	information	NN
9878	19	56	in	in	IN
9878	19	57	PDF	PDF	NNP
9878	19	58	/	/	SYM
9878	19	59	A	A	NNP
9878	19	60	,	,	,
9878	19	61	the	the	DT
9878	19	62	goals	goal	NNS
9878	19	63	of	of	IN
9878	19	64	this	this	DT
9878	19	65	article	article	NN
9878	19	66	are	be	VBP
9878	19	67	threefold	threefold	JJ
9878	19	68	:	:	:
9878	19	69	1	1	LS
9878	19	70	.	.	.
9878	19	71	present	present	JJ
9878	19	72	real	real	JJ
9878	19	73	-	-	HYPH
9878	19	74	life	life	NN
9878	19	75	experience	experience	NN
9878	19	76	of	of	IN
9878	19	77	converting	convert	VBG
9878	19	78	TIFFs	TIFFs	NNPS
9878	19	79	/	/	SYM
9878	19	80	JPEG2000s	JPEG2000s	NNP
9878	19	81	to	to	IN
9878	19	82	PDF	PDF	NNP
9878	19	83	/	/	SYM
9878	19	84	A	a	NN
9878	19	85	and	and	CC
9878	19	86	back	back	NN
9878	19	87	,	,	,
9878	19	88	along	along	IN
9878	19	89	with	with	IN
9878	19	90	image	image	NN
9878	19	91	metadata	metadata	NN
9878	19	92	2	2	CD
9878	19	93	.	.	.
9878	19	94	test	test	VB
9878	19	95	open	open	JJ
9878	19	96	source	source	NN
9878	19	97	libraries	library	NNS
9878	19	98	to	to	TO
9878	19	99	create	create	VB
9878	19	100	and	and	CC
9878	19	101	manipulate	manipulate	VB
9878	19	102	images	image	NNS
9878	19	103	,	,	,
9878	19	104	image	image	NN
9878	19	105	metadata	metadata	NN
9878	19	106	,	,	,
9878	19	107	and	and	CC
9878	19	108	PDF	PDF	NNP
9878	19	109	/	/	SYM
9878	19	110	A	A	NNP
9878	19	111	3	3	CD
9878	19	112	.	.	.
9878	19	113	validate	validate	NN
9878	19	114	generated	generate	VBD
9878	19	115	PDF	PDF	NNP
9878	19	116	/	/	,
9878	19	117	As	as	IN
9878	19	118	with	with	IN
9878	19	119	the	the	DT
9878	19	120	first	first	JJ
9878	19	121	legitimate	legitimate	JJ
9878	19	122	validator	validator	NN
9878	19	123	for	for	IN
9878	19	124	PDF	PDF	NNP
9878	19	125	/	/	SYM
9878	19	126	A	a	DT
9878	19	127	validation	validation	NN
9878	19	128	The	the	DT
9878	19	129	tasks	task	NNS
9878	19	130	included	include	VBD
9878	19	131	the	the	DT
9878	19	132	following	follow	VBG
9878	19	133	:	:	:
9878	19	134	●	●	NFP
9878	19	135	Convert	convert	VB
9878	19	136	all	all	PDT
9878	19	137	the	the	DT
9878	19	138	master	master	NN
9878	19	139	files	file	NNS
9878	19	140	in	in	IN
9878	19	141	TIFFs	TIFFs	NNP
9878	19	142	/	/	SYM
9878	19	143	JPEG2000	JPEG2000	NNP
9878	19	144	from	from	IN
9878	19	145	digitization	digitization	NN
9878	19	146	of	of	IN
9878	19	147	text	text	NN
9878	19	148	documents	document	NNS
9878	19	149	into	into	IN
9878	19	150	single	single	JJ
9878	19	151	PDF	pdf	NN
9878	19	152	/	/	,
9878	19	153	A	a	DT
9878	19	154	files	file	NNS
9878	19	155	losslessly	losslessly	RB
9878	19	156	.	.	.
9878	20	1	One	one	CD
9878	20	2	document	document	NN
9878	20	3	,	,	,
9878	20	4	one	one	CD
9878	20	5	PDF	PDF	NNP
9878	20	6	/	/	,
9878	20	7	A	a	DT
9878	20	8	file	file	NN
9878	20	9	.	.	.
9878	21	1	●	●	NFP
9878	21	2	Evaluate	evaluate	VB
9878	21	3	and	and	CC
9878	21	4	extract	extract	VB
9878	21	5	metadata	metadata	NN
9878	21	6	from	from	IN
9878	21	7	each	each	DT
9878	21	8	TIFF	TIFF	NNP
9878	21	9	/	/	SYM
9878	21	10	JPEG2000	JPEG2000	NNP
9878	21	11	image	image	NN
9878	21	12	and	and	CC
9878	21	13	encode	encode	VB
9878	21	14	it	-PRON-	PRP
9878	21	15	along	along	RP
9878	21	16	with	with	IN
9878	21	17	its	-PRON-	PRP$
9878	21	18	image	image	NN
9878	21	19	when	when	WRB
9878	21	20	creating	create	VBG
9878	21	21	the	the	DT
9878	21	22	corresponding	correspond	VBG
9878	21	23	PDF	PDF	NNP
9878	21	24	/	/	,
9878	21	25	A	a	DT
9878	21	26	file	file	NN
9878	21	27	.	.	.
9878	22	1	●	●	NFP
9878	22	2	Demonstrate	demonstrate	VB
9878	22	3	the	the	DT
9878	22	4	runtimes	runtime	NNS
9878	22	5	of	of	IN
9878	22	6	the	the	DT
9878	22	7	above	above	JJ
9878	22	8	tasks	task	NNS
9878	22	9	for	for	IN
9878	22	10	feasibility	feasibility	NN
9878	22	11	evaluation	evaluation	NN
9878	22	12	.	.	.
9878	23	1	●	●	NFP
9878	23	2	Validate	validate	VB
9878	23	3	the	the	DT
9878	23	4	PDF	pdf	NN
9878	23	5	/	/	,
9878	23	6	A	a	DT
9878	23	7	files	file	NNS
9878	23	8	against	against	IN
9878	23	9	the	the	DT
9878	23	10	newly	newly	RB
9878	23	11	released	release	VBN
9878	23	12	open	open	JJ
9878	23	13	source	source	NN
9878	23	14	PDF	PDF	NNP
9878	23	15	/	/	,
9878	23	16	A	a	DT
9878	23	17	validator	validator	NN
9878	23	18	veraPDF	verapdf	NN
9878	23	19	.	.	.
9878	24	1	●	●	NFP
9878	24	2	Extract	extract	VB
9878	24	3	each	each	DT
9878	24	4	digital	digital	JJ
9878	24	5	image	image	NN
9878	24	6	from	from	IN
9878	24	7	the	the	DT
9878	24	8	PDF	PDF	NNP
9878	24	9	/	/	SYM
9878	24	10	A	a	DT
9878	24	11	file	file	NN
9878	24	12	back	back	RB
9878	24	13	to	to	IN
9878	24	14	its	-PRON-	PRP$
9878	24	15	original	original	JJ
9878	24	16	master	master	NN
9878	24	17	image	image	NN
9878	24	18	files	file	NNS
9878	24	19	along	along	IN
9878	24	20	with	with	IN
9878	24	21	associated	associated	JJ
9878	24	22	metadata	metadata	NN
9878	24	23	.	.	.
9878	25	1	●	●	NFP
9878	25	2	Verify	verify	VB
9878	25	3	the	the	DT
9878	25	4	extracted	extract	VBN
9878	25	5	image	image	NN
9878	25	6	files	file	NNS
9878	25	7	in	in	IN
9878	25	8	the	the	DT
9878	25	9	back	back	JJ
9878	25	10	-	-	HYPH
9878	25	11	and	and	CC
9878	25	12	-	-	HYPH
9878	25	13	forth	forth	NN
9878	25	14	conversion	conversion	NN
9878	25	15	process	process	NN
9878	25	16	against	against	IN
9878	25	17	the	the	DT
9878	25	18	original	original	JJ
9878	25	19	master	master	NN
9878	25	20	image	image	NN
9878	25	21	files	file	VBZ
9878	25	22	Choices	Choices	NNPS
9878	25	23	of	of	IN
9878	25	24	PDF	PDF	NNP
9878	25	25	/	/	SYM
9878	25	26	A	A	NNP
9878	25	27	Standards	Standards	NNPS
9878	25	28	and	and	CC
9878	25	29	Conformance	Conformance	NNP
9878	25	30	Level	Level	NNP
9878	25	31	This	this	DT
9878	25	32	article	article	NN
9878	25	33	demonstrates	demonstrate	VBZ
9878	25	34	using	use	VBG
9878	25	35	PDF	PDF	NNP
9878	25	36	/	/	SYM
9878	25	37	A-2b	A-2b	NNP
9878	25	38	as	as	IN
9878	25	39	a	a	DT
9878	25	40	self	self	NN
9878	25	41	-	-	HYPH
9878	25	42	contained	contain	VBN
9878	25	43	self	self	NN
9878	25	44	-	-	HYPH
9878	25	45	describing	describe	VBG
9878	25	46	file	file	NN
9878	25	47	format	format	NN
9878	25	48	.	.	.
9878	26	1	Currently	currently	RB
9878	26	2	,	,	,
9878	26	3	there	there	EX
9878	26	4	are	be	VBP
9878	26	5	three	three	CD
9878	26	6	related	related	JJ
9878	26	7	PDF	PDF	NNP
9878	26	8	/	/	,
9878	26	9	A	a	DT
9878	26	10	standards	standard	NNS
9878	26	11	(	(	-LRB-
9878	26	12	PDF	PDF	NNP
9878	26	13	/	/	SYM
9878	26	14	A-1	A-1	NNP
9878	26	15	,	,	,
9878	26	16	PDF	PDF	NNP
9878	26	17	/	/	SYM
9878	26	18	A-2	A-2	NNP
9878	26	19	,	,	,
9878	26	20	and	and	CC
9878	26	21	PDF	PDF	NNP
9878	26	22	/	/	SYM
9878	26	23	A-3	A-3	NNP
9878	26	24	)	)	-RRB-
9878	26	25	,	,	,
9878	26	26	each	each	DT
9878	26	27	with	with	IN
9878	26	28	INFORMATION	INFORMATION	NNP
9878	26	29	TECHNOLOGY	TECHNOLOGY	NNP
9878	26	30	AND	and	CC
9878	26	31	LIBRARIES	library	NNS
9878	26	32	|	|	NNP
9878	26	33	MARCH	MARCH	NNP
9878	26	34	2018	2018	CD
9878	26	35	54	54	CD
9878	26	36	three	three	CD
9878	26	37	conformance	conformance	NN
9878	26	38	levels	level	NNS
9878	26	39	(	(	-LRB-
9878	26	40	a	a	DT
9878	26	41	,	,	,
9878	26	42	b	b	NN
9878	26	43	,	,	,
9878	26	44	and	and	CC
9878	26	45	u	u	NNP
9878	26	46	)	)	-RRB-
9878	26	47	.	.	.
9878	27	1	The	the	DT
9878	27	2	reasons	reason	NNS
9878	27	3	for	for	IN
9878	27	4	choosing	choose	VBG
9878	27	5	PDF	PDF	NNP
9878	27	6	/	/	SYM
9878	27	7	A-2	A-2	NNP
9878	27	8	(	(	-LRB-
9878	27	9	instead	instead	RB
9878	27	10	of	of	IN
9878	27	11	PDF	PDF	NNP
9878	27	12	/	/	SYM
9878	27	13	A-1	A-1	NNP
9878	27	14	or	or	CC
9878	27	15	PDF	PDF	NNP
9878	27	16	/	/	SYM
9878	27	17	A-3	A-3	NNP
9878	27	18	)	)	-RRB-
9878	27	19	are	be	VBP
9878	27	20	the	the	DT
9878	27	21	following	follow	VBG
9878	27	22	:	:	:
9878	27	23	●	●	NFP
9878	27	24	PDF	PDF	NNP
9878	27	25	/	/	SYM
9878	27	26	A-1	A-1	NNP
9878	27	27	is	be	VBZ
9878	27	28	based	base	VBN
9878	27	29	on	on	IN
9878	27	30	PDF	PDF	NNP
9878	27	31	1.4	1.4	CD
9878	27	32	.	.	.
9878	28	1	In	in	IN
9878	28	2	this	this	DT
9878	28	3	standard	standard	NN
9878	28	4	,	,	,
9878	28	5	images	image	NNS
9878	28	6	coded	code	VBN
9878	28	7	in	in	IN
9878	28	8	PDF	PDF	NNP
9878	28	9	/	/	SYM
9878	28	10	A-1	A-1	NNP
9878	28	11	can	can	MD
9878	28	12	not	not	RB
9878	28	13	use	use	VB
9878	28	14	JPEG2000	JPEG2000	NNP
9878	28	15	compression	compression	NN
9878	28	16	(	(	-LRB-
9878	28	17	named	name	VBN
9878	28	18	in	in	IN
9878	28	19	PDF	PDF	NNP
9878	28	20	/	/	,
9878	28	21	A	A	NNP
9878	28	22	as	as	IN
9878	28	23	JPXDecode	jpxdecode	NN
9878	28	24	)	)	-RRB-
9878	28	25	.	.	.
9878	29	1	One	one	PRP
9878	29	2	can	can	MD
9878	29	3	still	still	RB
9878	29	4	convert	convert	VB
9878	29	5	TIFFs	TIFFs	NNP
9878	29	6	to	to	IN
9878	29	7	PDF	PDF	NNP
9878	29	8	/	/	SYM
9878	29	9	A-1	A-1	NNP
9878	29	10	using	use	VBG
9878	29	11	other	other	JJ
9878	29	12	lossless	lossless	JJ
9878	29	13	compression	compression	NN
9878	29	14	methods	method	NNS
9878	29	15	such	such	JJ
9878	29	16	as	as	IN
9878	29	17	LZW	LZW	NNP
9878	29	18	.	.	.
9878	30	1	However	however	RB
9878	30	2	,	,	,
9878	30	3	the	the	DT
9878	30	4	space-	space-	JJ
9878	30	5	saving	save	VBG
9878	30	6	benefits	benefit	NNS
9878	30	7	of	of	IN
9878	30	8	JPEG2000	JPEG2000	NNP
9878	30	9	compression	compression	NN
9878	30	10	over	over	IN
9878	30	11	other	other	JJ
9878	30	12	methods	method	NNS
9878	30	13	would	would	MD
9878	30	14	not	not	RB
9878	30	15	be	be	VB
9878	30	16	utilized	utilize	VBN
9878	30	17	.	.	.
9878	31	1	●	●	NFP
9878	31	2	PDF	PDF	NNP
9878	31	3	/	/	SYM
9878	31	4	A-2	A-2	NNP
9878	31	5	and	and	CC
9878	31	6	PDF	PDF	NNP
9878	31	7	/	/	SYM
9878	31	8	A-3	A-3	NNP
9878	31	9	are	be	VBP
9878	31	10	based	base	VBN
9878	31	11	on	on	IN
9878	31	12	PDF	PDF	NNP
9878	31	13	1.7	1.7	CD
9878	31	14	.	.	.
9878	32	1	One	one	CD
9878	32	2	significant	significant	JJ
9878	32	3	feature	feature	NN
9878	32	4	of	of	IN
9878	32	5	PDF	PDF	NNP
9878	32	6	1.7	1.7	CD
9878	32	7	is	be	VBZ
9878	32	8	that	that	IN
9878	32	9	it	-PRON-	PRP
9878	32	10	supports	support	VBZ
9878	32	11	JPEG2000	JPEG2000	NNP
9878	32	12	compression	compression	NN
9878	32	13	,	,	,
9878	32	14	which	which	WDT
9878	32	15	saves	save	VBZ
9878	32	16	40–60	40–60	CD
9878	32	17	percent	percent	NN
9878	32	18	of	of	IN
9878	32	19	space	space	NN
9878	32	20	for	for	IN
9878	32	21	raster	raster	NN
9878	32	22	images	image	NNS
9878	32	23	compared	compare	VBN
9878	32	24	to	to	IN
9878	32	25	uncompressed	uncompress	VBN
9878	32	26	TIFFs	TIFFs	NNPS
9878	32	27	.	.	.
9878	33	1	●	●	NFP
9878	33	2	PDF	PDF	NNP
9878	33	3	/	/	SYM
9878	33	4	A-3	A-3	NNP
9878	33	5	has	have	VBZ
9878	33	6	one	one	CD
9878	33	7	major	major	JJ
9878	33	8	feature	feature	NN
9878	33	9	that	that	WDT
9878	33	10	PDF	PDF	NNP
9878	33	11	/	/	SYM
9878	33	12	A-2	A-2	NNP
9878	33	13	does	do	VBZ
9878	33	14	not	not	RB
9878	33	15	have	have	VB
9878	33	16	,	,	,
9878	33	17	which	which	WDT
9878	33	18	is	be	VBZ
9878	33	19	to	to	TO
9878	33	20	allow	allow	VB
9878	33	21	arbitrary	arbitrary	JJ
9878	33	22	files	file	NNS
9878	33	23	to	to	TO
9878	33	24	be	be	VB
9878	33	25	embedded	embed	VBN
9878	33	26	within	within	IN
9878	33	27	the	the	DT
9878	33	28	PDF	PDF	NNP
9878	33	29	file	file	NN
9878	33	30	.	.	.
9878	34	1	In	in	IN
9878	34	2	this	this	DT
9878	34	3	case	case	NN
9878	34	4	,	,	,
9878	34	5	there	there	EX
9878	34	6	is	be	VBZ
9878	34	7	no	no	DT
9878	34	8	file	file	NN
9878	34	9	to	to	TO
9878	34	10	be	be	VB
9878	34	11	embedded	embed	VBN
9878	34	12	.	.	.
9878	35	1	The	the	DT
9878	35	2	authors	author	NNS
9878	35	3	chose	choose	VBD
9878	35	4	conformance	conformance	NN
9878	35	5	level	level	NN
9878	35	6	b	b	NN
9878	35	7	for	for	IN
9878	35	8	simplicity	simplicity	NN
9878	35	9	.	.	.
9878	36	1	●	●	NFP
9878	36	2	b	b	NN
9878	36	3	is	be	VBZ
9878	36	4	basic	basic	JJ
9878	36	5	conformance	conformance	NN
9878	36	6	,	,	,
9878	36	7	which	which	WDT
9878	36	8	requires	require	VBZ
9878	36	9	only	only	RB
9878	36	10	necessary	necessary	JJ
9878	36	11	components	component	NNS
9878	36	12	(	(	-LRB-
9878	36	13	e.g.	e.g.	RB
9878	36	14	,	,	,
9878	36	15	all	all	DT
9878	36	16	fonts	font	NNS
9878	36	17	embedded	embed	VBN
9878	36	18	in	in	IN
9878	36	19	the	the	DT
9878	36	20	PDF	pdf	NN
9878	36	21	)	)	-RRB-
9878	36	22	for	for	IN
9878	36	23	reproduction	reproduction	NN
9878	36	24	of	of	IN
9878	36	25	a	a	DT
9878	36	26	document	document	NN
9878	36	27	’s	’s	POS
9878	36	28	visual	visual	JJ
9878	36	29	appearance	appearance	NN
9878	36	30	.	.	.
9878	37	1	●	●	NFP
9878	37	2	a	a	DT
9878	37	3	is	be	VBZ
9878	37	4	accessible	accessible	JJ
9878	37	5	conformance	conformance	NN
9878	37	6	,	,	,
9878	37	7	which	which	WDT
9878	37	8	means	mean	VBZ
9878	37	9	b	b	NNP
9878	37	10	conformance	conformance	NN
9878	37	11	level	level	NN
9878	37	12	plus	plus	CC
9878	37	13	additional	additional	JJ
9878	37	14	accessibility	accessibility	NN
9878	37	15	(	(	-LRB-
9878	37	16	structural	structural	JJ
9878	37	17	and	and	CC
9878	37	18	semantic	semantic	JJ
9878	37	19	features	feature	NNS
9878	37	20	such	such	JJ
9878	37	21	as	as	IN
9878	37	22	document	document	NN
9878	37	23	structure	structure	NN
9878	37	24	)	)	-RRB-
9878	37	25	.	.	.
9878	38	1	One	one	PRP
9878	38	2	can	can	MD
9878	38	3	add	add	VB
9878	38	4	tags	tag	NNS
9878	38	5	to	to	TO
9878	38	6	convert	convert	VB
9878	38	7	PDF/2b	pdf/2b	NN
9878	38	8	to	to	IN
9878	38	9	PDF/2a	pdf/2a	XX
9878	38	10	.	.	.
9878	39	1	●	●	NFP
9878	39	2	u	u	NNP
9878	39	3	represents	represent	VBZ
9878	39	4	a	a	DT
9878	39	5	conformance	conformance	NN
9878	39	6	level	level	NN
9878	39	7	with	with	IN
9878	39	8	the	the	DT
9878	39	9	additional	additional	JJ
9878	39	10	requirement	requirement	NN
9878	39	11	that	that	IN
9878	39	12	all	all	DT
9878	39	13	text	text	NN
9878	39	14	in	in	IN
9878	39	15	the	the	DT
9878	39	16	document	document	NN
9878	39	17	have	have	VBP
9878	39	18	Unicode	Unicode	NNP
9878	39	19	equivalents	equivalent	NNS
9878	39	20	.	.	.
9878	40	1	This	this	DT
9878	40	2	article	article	NN
9878	40	3	does	do	VBZ
9878	40	4	not	not	RB
9878	40	5	cover	cover	VB
9878	40	6	any	any	DT
9878	40	7	post	post	NN
9878	40	8	-	-	JJ
9878	40	9	processing	processing	NN
9878	40	10	of	of	IN
9878	40	11	additional	additional	JJ
9878	40	12	manual	manual	JJ
9878	40	13	or	or	CC
9878	40	14	computational	computational	JJ
9878	40	15	features	feature	NNS
9878	40	16	such	such	JJ
9878	40	17	as	as	IN
9878	40	18	adding	add	VBG
9878	40	19	OCR	ocr	NN
9878	40	20	text	text	NN
9878	40	21	to	to	IN
9878	40	22	the	the	DT
9878	40	23	generated	generate	VBN
9878	40	24	PDF	PDF	NNP
9878	40	25	/	/	,
9878	40	26	A	a	DT
9878	40	27	files	file	NNS
9878	40	28	.	.	.
9878	41	1	These	these	DT
9878	41	2	features	feature	NNS
9878	41	3	do	do	VBP
9878	41	4	not	not	RB
9878	41	5	help	help	VB
9878	41	6	faithfully	faithfully	RB
9878	41	7	capture	capture	VB
9878	41	8	the	the	DT
9878	41	9	look	look	NN
9878	41	10	and	and	CC
9878	41	11	feel	feel	NN
9878	41	12	of	of	IN
9878	41	13	original	original	JJ
9878	41	14	pages	page	NNS
9878	41	15	in	in	IN
9878	41	16	digitization	digitization	NN
9878	41	17	,	,	,
9878	41	18	and	and	CC
9878	41	19	they	-PRON-	PRP
9878	41	20	can	can	MD
9878	41	21	be	be	VB
9878	41	22	added	add	VBN
9878	41	23	or	or	CC
9878	41	24	updated	update	VBN
9878	41	25	later	later	RB
9878	41	26	without	without	IN
9878	41	27	any	any	DT
9878	41	28	loss	loss	NN
9878	41	29	of	of	IN
9878	41	30	information	information	NN
9878	41	31	.	.	.
9878	42	1	In	in	IN
9878	42	2	addition	addition	NN
9878	42	3	,	,	,
9878	42	4	OCR	ocr	NN
9878	42	5	results	result	NNS
9878	42	6	rely	rely	VBP
9878	42	7	on	on	IN
9878	42	8	the	the	DT
9878	42	9	availability	availability	NN
9878	42	10	of	of	IN
9878	42	11	OCR	ocr	NN
9878	42	12	engines	engine	NNS
9878	42	13	for	for	IN
9878	42	14	the	the	DT
9878	42	15	document	document	NN
9878	42	16	’s	’s	POS
9878	42	17	language	language	NN
9878	42	18	,	,	,
9878	42	19	and	and	CC
9878	42	20	results	result	NNS
9878	42	21	can	can	MD
9878	42	22	vary	vary	VB
9878	42	23	between	between	IN
9878	42	24	different	different	JJ
9878	42	25	OCR	ocr	NN
9878	42	26	engines	engine	NNS
9878	42	27	over	over	IN
9878	42	28	time	time	NN
9878	42	29	.	.	.
9878	43	1	OCR	ocr	NN
9878	43	2	technology	technology	NN
9878	43	3	is	be	VBZ
9878	43	4	getting	get	VBG
9878	43	5	better	well	JJR
9878	43	6	and	and	CC
9878	43	7	will	will	MD
9878	43	8	produce	produce	VB
9878	43	9	better	well	JJR
9878	43	10	results	result	NNS
9878	43	11	in	in	IN
9878	43	12	the	the	DT
9878	43	13	future	future	NN
9878	43	14	.	.	.
9878	44	1	For	for	IN
9878	44	2	example	example	NN
9878	44	3	,	,	,
9878	44	4	current	current	JJ
9878	44	5	OCR	ocr	NN
9878	44	6	technology	technology	NN
9878	44	7	for	for	IN
9878	44	8	English	English	NNP
9878	44	9	gives	give	VBZ
9878	44	10	very	very	RB
9878	44	11	reliable	reliable	JJ
9878	44	12	(	(	-LRB-
9878	44	13	more	more	JJR
9878	44	14	than	than	IN
9878	44	15	90	90	CD
9878	44	16	percent	percent	NN
9878	44	17	)	)	-RRB-
9878	44	18	accuracy	accuracy	NN
9878	44	19	.	.	.
9878	45	1	In	in	IN
9878	45	2	comparison	comparison	NN
9878	45	3	,	,	,
9878	45	4	traditional	traditional	JJ
9878	45	5	Chinese	chinese	JJ
9878	45	6	manuscripts	manuscript	NNS
9878	45	7	and	and	CC
9878	45	8	Pashto	Pashto	NNP
9878	45	9	/	/	SYM
9878	45	10	Persian	Persian	NNP
9878	45	11	give	give	VBP
9878	45	12	unacceptably	unacceptably	RB
9878	45	13	low	low	JJ
9878	45	14	accuracy	accuracy	NN
9878	45	15	(	(	-LRB-
9878	45	16	less	less	JJR
9878	45	17	than	than	IN
9878	45	18	60	60	CD
9878	45	19	percent	percent	NN
9878	45	20	)	)	-RRB-
9878	45	21	.	.	.
9878	46	1	The	the	DT
9878	46	2	cutting	cutting	JJ
9878	46	3	edge	edge	NN
9878	46	4	on	on	IN
9878	46	5	OCR	ocr	NN
9878	46	6	engines	engine	NNS
9878	46	7	has	have	VBZ
9878	46	8	started	start	VBN
9878	46	9	to	to	TO
9878	46	10	utilize	utilize	VB
9878	46	11	artificial	artificial	JJ
9878	46	12	intelligence	intelligence	NN
9878	46	13	networks	network	NNS
9878	46	14	,	,	,
9878	46	15	and	and	CC
9878	46	16	the	the	DT
9878	46	17	authors	author	NNS
9878	46	18	believe	believe	VBP
9878	46	19	that	that	IN
9878	46	20	a	a	DT
9878	46	21	breakthrough	breakthrough	NN
9878	46	22	will	will	MD
9878	46	23	happen	happen	VB
9878	46	24	soon	soon	RB
9878	46	25	.	.	.
9878	47	1	Data	Data	NNP
9878	47	2	Source	Source	NNP
9878	47	3	The	the	DT
9878	47	4	University	University	NNP
9878	47	5	of	of	IN
9878	47	6	Arizona	Arizona	NNP
9878	47	7	Libraries	Libraries	NNPS
9878	47	8	(	(	-LRB-
9878	47	9	UAL	UAL	NNP
9878	47	10	)	)	-RRB-
9878	47	11	and	and	CC
9878	47	12	Afghanistan	Afghanistan	NNP
9878	47	13	Center	Center	NNP
9878	47	14	at	at	IN
9878	47	15	Kabul	Kabul	NNP
9878	47	16	University	University	NNP
9878	47	17	(	(	-LRB-
9878	47	18	ACKU	ACKU	NNP
9878	47	19	)	)	-RRB-
9878	47	20	have	have	VBP
9878	47	21	been	be	VBN
9878	47	22	partnering	partner	VBG
9878	47	23	to	to	TO
9878	47	24	digitize	digitize	VB
9878	47	25	and	and	CC
9878	47	26	preserve	preserve	VB
9878	47	27	ACKU	ACKU	NNP
9878	47	28	’s	’s	POS
9878	47	29	permanent	permanent	JJ
9878	47	30	collection	collection	NN
9878	47	31	held	hold	VBN
9878	47	32	in	in	IN
9878	47	33	Kabul	Kabul	NNP
9878	47	34	.	.	.
9878	48	1	This	this	DT
9878	48	2	collaborative	collaborative	JJ
9878	48	3	project	project	NN
9878	48	4	created	create	VBD
9878	48	5	the	the	DT
9878	48	6	largest	large	JJS
9878	48	7	Afghan	afghan	JJ
9878	48	8	digital	digital	JJ
9878	48	9	repository	repository	NN
9878	48	10	in	in	IN
9878	48	11	the	the	DT
9878	48	12	world	world	NN
9878	48	13	.	.	.
9878	49	1	Currently	currently	RB
9878	49	2	the	the	DT
9878	49	3	Afghan	afghan	JJ
9878	49	4	digital	digital	JJ
9878	49	5	repository	repository	NN
9878	49	6	(	(	-LRB-
9878	49	7	http://www.afghandata.org	http://www.afghandata.org	NNP
9878	49	8	)	)	-RRB-
9878	49	9	contains	contain	VBZ
9878	49	10	more	more	JJR
9878	49	11	than	than	IN
9878	49	12	fifteen	fifteen	CD
9878	49	13	thousand	thousand	CD
9878	49	14	titles	title	NNS
9878	49	15	and	and	CC
9878	49	16	1.6	1.6	CD
9878	49	17	million	million	CD
9878	49	18	pages	page	NNS
9878	49	19	of	of	IN
9878	49	20	documents	document	NNS
9878	49	21	.	.	.
9878	50	1	Digitization	digitization	NN
9878	50	2	of	of	IN
9878	50	3	these	these	DT
9878	50	4	text	text	NN
9878	50	5	documents	document	NNS
9878	50	6	follows	follow	VBZ
9878	50	7	the	the	DT
9878	50	8	previous	previous	JJ
9878	50	9	version	version	NN
9878	50	10	of	of	IN
9878	50	11	the	the	DT
9878	50	12	FADGI	FADGI	NNP
9878	50	13	guideline	guideline	NN
9878	50	14	,	,	,
9878	50	15	which	which	WDT
9878	50	16	recommended	recommend	VBD
9878	50	17	scanning	scanning	NN
9878	50	18	each	each	DT
9878	50	19	page	page	NN
9878	50	20	of	of	IN
9878	50	21	a	a	DT
9878	50	22	text	text	NN
9878	50	23	document	document	NN
9878	50	24	into	into	IN
9878	50	25	a	a	DT
9878	50	26	separate	separate	JJ
9878	50	27	TIFF	TIFF	NNP
9878	50	28	file	file	NN
9878	50	29	as	as	IN
9878	50	30	the	the	DT
9878	50	31	master	master	NN
9878	50	32	file	file	NN
9878	50	33	.	.	.
9878	51	1	These	these	DT
9878	51	2	TIFFs	TIFFs	NNPS
9878	51	3	were	be	VBD
9878	51	4	organized	organize	VBN
9878	51	5	by	by	IN
9878	51	6	directories	directory	NNS
9878	51	7	in	in	IN
9878	51	8	a	a	DT
9878	51	9	file	file	NN
9878	51	10	system	system	NN
9878	51	11	,	,	,
9878	51	12	where	where	WRB
9878	51	13	each	each	DT
9878	51	14	directory	directory	NN
9878	51	15	represents	represent	VBZ
9878	51	16	a	a	DT
9878	51	17	corresponding	corresponding	JJ
9878	51	18	document	document	NN
9878	51	19	containing	contain	VBG
9878	51	20	all	all	PDT
9878	51	21	the	the	DT
9878	51	22	scanned	scan	VBN
9878	51	23	pages	page	NNS
9878	51	24	of	of	IN
9878	51	25	this	this	DT
9878	51	26	title	title	NN
9878	51	27	.	.	.
9878	52	1	An	an	DT
9878	52	2	example	example	NN
9878	52	3	of	of	IN
9878	52	4	the	the	DT
9878	52	5	directory	directory	NN
9878	52	6	structure	structure	NN
9878	52	7	can	can	MD
9878	52	8	be	be	VB
9878	52	9	found	find	VBN
9878	52	10	in	in	IN
9878	52	11	Han	Han	NNP
9878	52	12	’s	’s	POS
9878	52	13	article	article	NN
9878	52	14	.	.	.
9878	53	1	http://www.afghandata.org/	http://www.afghandata.org/	NFP
9878	53	2	DIGITIZATION	DIGITIZATION	NNS
9878	53	3	OF	of	IN
9878	53	4	TEXT	text	NN
9878	53	5	DOCUMENTS	documents	NN
9878	53	6	USING	USING	NNP
9878	53	7	PDF	PDF	NNP
9878	53	8	/	/	SYM
9878	53	9	A	A	NNP
9878	53	10	|	|	NNP
9878	53	11	HAN	HAN	NNP
9878	53	12	AND	and	CC
9878	53	13	WAN	WAN	NNP
9878	53	14	55	55	CD
9878	53	15	HTTPS://DOI.ORG/10.6017	HTTPS://DOI.ORG/10.6017	NNS
9878	53	16	/	/	SYM
9878	53	17	ITAL.V37I1.9878	ITAL.V37I1.9878	NNP
9878	53	18	PDF	PDF	NNP
9878	53	19	/	/	SYM
9878	53	20	A	A	NNP
9878	53	21	and	and	CC
9878	53	22	Image	Image	NNP
9878	53	23	Manipulation	Manipulation	NNP
9878	53	24	Tools	Tools	NNP
9878	53	25	There	there	EX
9878	53	26	are	be	VBP
9878	53	27	a	a	DT
9878	53	28	few	few	JJ
9878	53	29	open	open	JJ
9878	53	30	source	source	NN
9878	53	31	and	and	CC
9878	53	32	proprietary	proprietary	JJ
9878	53	33	PDF	PDF	NNP
9878	53	34	software	software	NN
9878	53	35	development	development	NN
9878	53	36	kits	kit	NNS
9878	53	37	(	(	-LRB-
9878	53	38	SDK	SDK	NNP
9878	53	39	)	)	-RRB-
9878	53	40	.	.	.
9878	54	1	Adobe	Adobe	NNP
9878	54	2	PDF	PDF	NNP
9878	54	3	Library	Library	NNP
9878	54	4	and	and	CC
9878	54	5	Foxit	Foxit	NNP
9878	54	6	SDK	SDK	NNP
9878	54	7	are	be	VBP
9878	54	8	the	the	DT
9878	54	9	most	most	RBS
9878	54	10	well	well	RB
9878	54	11	-	-	HYPH
9878	54	12	known	know	VBN
9878	54	13	commercial	commercial	JJ
9878	54	14	tools	tool	NNS
9878	54	15	to	to	TO
9878	54	16	manipulate	manipulate	VB
9878	54	17	PDFs	pdf	NNS
9878	54	18	.	.	.
9878	55	1	To	to	TO
9878	55	2	show	show	VB
9878	55	3	readers	reader	NNS
9878	55	4	that	that	IN
9878	55	5	they	-PRON-	PRP
9878	55	6	can	can	MD
9878	55	7	manipulate	manipulate	VB
9878	55	8	and	and	CC
9878	55	9	generate	generate	VB
9878	55	10	PDF	PDF	NNP
9878	55	11	/	/	,
9878	55	12	A	a	DT
9878	55	13	documents	document	NNS
9878	55	14	themselves	-PRON-	PRP
9878	55	15	,	,	,
9878	55	16	open	open	JJ
9878	55	17	source	source	NN
9878	55	18	software	software	NN
9878	55	19	,	,	,
9878	55	20	rather	rather	RB
9878	55	21	than	than	IN
9878	55	22	commercial	commercial	JJ
9878	55	23	tools	tool	NNS
9878	55	24	,	,	,
9878	55	25	was	be	VBD
9878	55	26	used	use	VBN
9878	55	27	.	.	.
9878	56	1	Currently	currently	RB
9878	56	2	,	,	,
9878	56	3	only	only	RB
9878	56	4	a	a	DT
9878	56	5	very	very	RB
9878	56	6	limited	limited	JJ
9878	56	7	number	number	NN
9878	56	8	of	of	IN
9878	56	9	open	open	JJ
9878	56	10	source	source	NN
9878	56	11	PDF	PDF	NNP
9878	56	12	SDKs	sdk	NNS
9878	56	13	are	be	VBP
9878	56	14	available	available	JJ
9878	56	15	,	,	,
9878	56	16	including	include	VBG
9878	56	17	iText	iText	NNP
9878	56	18	and	and	CC
9878	56	19	PDFBox	PDFBox	NNP
9878	56	20	.	.	.
9878	57	1	iText	iText	NNP
9878	57	2	was	be	VBD
9878	57	3	chosen	choose	VBN
9878	57	4	because	because	IN
9878	57	5	it	-PRON-	PRP
9878	57	6	has	have	VBZ
9878	57	7	g	g	NN
9878	57	8	ood	ood	JJ
9878	57	9	documentation	documentation	NN
9878	57	10	and	and	CC
9878	57	11	provides	provide	VBZ
9878	57	12	a	a	DT
9878	57	13	well	well	RB
9878	57	14	-	-	HYPH
9878	57	15	built	build	VBN
9878	57	16	set	set	NN
9878	57	17	of	of	IN
9878	57	18	APIs	api	NNS
9878	57	19	to	to	TO
9878	57	20	support	support	VB
9878	57	21	almost	almost	RB
9878	57	22	all	all	PDT
9878	57	23	the	the	DT
9878	57	24	PDF	PDF	NNP
9878	57	25	and	and	CC
9878	57	26	PDF	PDF	NNP
9878	57	27	/	/	SYM
9878	57	28	A	A	NNP
9878	57	29	features	feature	NNS
9878	57	30	.	.	.
9878	58	1	Initially	initially	RB
9878	58	2	written	write	VBN
9878	58	3	by	by	IN
9878	58	4	Bruno	Bruno	NNP
9878	58	5	Lowagie	Lowagie	NNP
9878	58	6	(	(	-LRB-
9878	58	7	who	who	WP
9878	58	8	was	be	VBD
9878	58	9	in	in	IN
9878	58	10	the	the	DT
9878	58	11	ISO	iso	NN
9878	58	12	PDF	PDF	NNP
9878	58	13	standard	standard	NN
9878	58	14	working	work	VBG
9878	58	15	group	group	NN
9878	58	16	)	)	-RRB-
9878	58	17	in	in	IN
9878	58	18	1998	1998	CD
9878	58	19	as	as	IN
9878	58	20	an	an	DT
9878	58	21	in	in	IN
9878	58	22	-	-	HYPH
9878	58	23	house	house	NN
9878	58	24	project	project	NN
9878	58	25	,	,	,
9878	58	26	Lowagie	Lowagie	NNP
9878	58	27	later	later	RB
9878	58	28	started	start	VBD
9878	58	29	up	up	RP
9878	58	30	his	-PRON-	PRP$
9878	58	31	own	own	JJ
9878	58	32	company	company	NN
9878	58	33	,	,	,
9878	58	34	iText	iText	NNP
9878	58	35	,	,	,
9878	58	36	and	and	CC
9878	58	37	published	publish	VBD
9878	58	38	iText	iText	NNP
9878	58	39	in	in	IN
9878	58	40	Action	Action	NNP
9878	58	41	with	with	IN
9878	58	42	many	many	JJ
9878	58	43	code	code	NN
9878	58	44	examples.6	examples.6	NN
9878	58	45	Moreover	moreover	RB
9878	58	46	,	,	,
9878	58	47	iText	iText	NNP
9878	58	48	has	have	VBZ
9878	58	49	Java	Java	NNP
9878	58	50	and	and	CC
9878	58	51	C	C	NNP
9878	58	52	#	#	$
9878	58	53	coding	code	VBG
9878	58	54	options	option	NNS
9878	58	55	with	with	IN
9878	58	56	good	good	JJ
9878	58	57	code	code	NN
9878	58	58	documentation	documentation	NN
9878	58	59	.	.	.
9878	59	1	It	-PRON-	PRP
9878	59	2	is	be	VBZ
9878	59	3	worth	worth	JJ
9878	59	4	mentioning	mention	VBG
9878	59	5	that	that	IN
9878	59	6	iText	iText	NNP
9878	59	7	has	have	VBZ
9878	59	8	different	different	JJ
9878	59	9	versions	version	NNS
9878	59	10	.	.	.
9878	60	1	The	the	DT
9878	60	2	author	author	NN
9878	60	3	used	use	VBD
9878	60	4	iText	iText	NNP
9878	60	5	5.5.10	5.5.10	CD
9878	60	6	and	and	CC
9878	60	7	5.4.4	5.4.4	CD
9878	60	8	.	.	.
9878	61	1	Using	use	VBG
9878	61	2	an	an	DT
9878	61	3	older	old	JJR
9878	61	4	version	version	NN
9878	61	5	in	in	IN
9878	61	6	our	-PRON-	PRP$
9878	61	7	implementation	implementation	NN
9878	61	8	generated	generate	VBD
9878	61	9	a	a	DT
9878	61	10	non	non	JJ
9878	61	11	-	-	JJ
9878	61	12	compatible	compatible	JJ
9878	61	13	PDF	PDF	NNP
9878	61	14	/	/	,
9878	61	15	A	a	DT
9878	61	16	file	file	NN
9878	61	17	because	because	IN
9878	61	18	the	the	DT
9878	61	19	it	-PRON-	PRP
9878	61	20	was	be	VBD
9878	61	21	not	not	RB
9878	61	22	aligned	align	VBN
9878	61	23	with	with	IN
9878	61	24	the	the	DT
9878	61	25	PDF	PDF	NNP
9878	61	26	/	/	SYM
9878	61	27	A	a	NN
9878	61	28	standard.7	standard.7	CD
9878	61	29	For	for	IN
9878	61	30	image	image	NN
9878	61	31	processing	processing	NN
9878	61	32	,	,	,
9878	61	33	there	there	EX
9878	61	34	were	be	VBD
9878	61	35	a	a	DT
9878	61	36	few	few	JJ
9878	61	37	popular	popular	JJ
9878	61	38	open	open	JJ
9878	61	39	source	source	NN
9878	61	40	options	option	NNS
9878	61	41	,	,	,
9878	61	42	including	include	VBG
9878	61	43	ImageMagick	ImageMagick	NNP
9878	61	44	and	and	CC
9878	61	45	GIMP	GIMP	NNP
9878	61	46	.	.	.
9878	62	1	ImageMagick	ImageMagick	NNP
9878	62	2	was	be	VBD
9878	62	3	chosen	choose	VBN
9878	62	4	because	because	IN
9878	62	5	of	of	IN
9878	62	6	its	-PRON-	PRP$
9878	62	7	popularity	popularity	NN
9878	62	8	,	,	,
9878	62	9	stability	stability	NN
9878	62	10	,	,	,
9878	62	11	and	and	CC
9878	62	12	cross	cross	JJ
9878	62	13	-	-	JJ
9878	62	14	platform	platform	JJ
9878	62	15	implementation	implementation	NN
9878	62	16	.	.	.
9878	63	1	Our	-PRON-	PRP$
9878	63	2	implementation	implementation	NN
9878	63	3	identified	identify	VBD
9878	63	4	one	one	CD
9878	63	5	issue	issue	NN
9878	63	6	with	with	IN
9878	63	7	ImageMagick	ImageMagick	NNP
9878	63	8	:	:	:
9878	63	9	the	the	DT
9878	63	10	current	current	JJ
9878	63	11	version	version	NN
9878	63	12	(	(	-LRB-
9878	63	13	7.0.4	7.0.4	NNP
9878	63	14	)	)	-RRB-
9878	63	15	could	could	MD
9878	63	16	not	not	RB
9878	63	17	retrieve	retrieve	VB
9878	63	18	all	all	PDT
9878	63	19	the	the	DT
9878	63	20	metadata	metadata	NN
9878	63	21	from	from	IN
9878	63	22	TIFF	TIFF	NNP
9878	63	23	files	file	NNS
9878	63	24	as	as	IN
9878	63	25	it	-PRON-	PRP
9878	63	26	did	do	VBD
9878	63	27	not	not	RB
9878	63	28	extract	extract	VB
9878	63	29	certain	certain	JJ
9878	63	30	information	information	NN
9878	63	31	such	such	JJ
9878	63	32	as	as	IN
9878	63	33	the	the	DT
9878	63	34	Image	Image	NNP
9878	63	35	File	File	NNP
9878	63	36	Directory	directory	NN
9878	63	37	and	and	CC
9878	63	38	color	color	NN
9878	63	39	profile	profile	NN
9878	63	40	.	.	.
9878	64	1	These	these	DT
9878	64	2	metadata	metadata	NN
9878	64	3	are	be	VBP
9878	64	4	critical	critical	JJ
9878	64	5	because	because	IN
9878	64	6	they	-PRON-	PRP
9878	64	7	are	be	VBP
9878	64	8	part	part	NN
9878	64	9	of	of	IN
9878	64	10	the	the	DT
9878	64	11	original	original	JJ
9878	64	12	data	datum	NNS
9878	64	13	from	from	IN
9878	64	14	digitization	digitization	NN
9878	64	15	.	.	.
9878	65	1	Unfortunately	unfortunately	RB
9878	65	2	,	,	,
9878	65	3	the	the	DT
9878	65	4	author	author	NN
9878	65	5	observed	observe	VBD
9878	65	6	that	that	IN
9878	65	7	some	some	DT
9878	65	8	image	image	NN
9878	65	9	editors	editor	NNS
9878	65	10	were	be	VBD
9878	65	11	unable	unable	JJ
9878	65	12	to	to	TO
9878	65	13	preserve	preserve	VB
9878	65	14	all	all	PDT
9878	65	15	the	the	DT
9878	65	16	metadata	metadata	NN
9878	65	17	from	from	IN
9878	65	18	the	the	DT
9878	65	19	image	image	NN
9878	65	20	files	file	NNS
9878	65	21	during	during	IN
9878	65	22	the	the	DT
9878	65	23	conversion	conversion	NN
9878	65	24	process	process	NN
9878	65	25	.	.	.
9878	66	1	Hart	Hart	NNP
9878	66	2	and	and	CC
9878	66	3	De	De	NNP
9878	66	4	Varies	Varies	NNP
9878	66	5	used	use	VBD
9878	66	6	case	case	NN
9878	66	7	studies	study	NNS
9878	66	8	to	to	TO
9878	66	9	show	show	VB
9878	66	10	the	the	DT
9878	66	11	vulnerability	vulnerability	NN
9878	66	12	of	of	IN
9878	66	13	metadata	metadata	NN
9878	66	14	,	,	,
9878	66	15	demonstrating	demonstrate	VBG
9878	66	16	metadata	metadata	NN
9878	66	17	elements	element	NNS
9878	66	18	in	in	IN
9878	66	19	a	a	DT
9878	66	20	digital	digital	JJ
9878	66	21	object	object	NN
9878	66	22	can	can	MD
9878	66	23	be	be	VB
9878	66	24	lost	lose	VBN
9878	66	25	and	and	CC
9878	66	26	corrupted	corrupt	VBN
9878	66	27	by	by	IN
9878	66	28	use	use	NN
9878	66	29	or	or	CC
9878	66	30	conversion	conversion	NN
9878	66	31	of	of	IN
9878	66	32	a	a	DT
9878	66	33	file	file	NN
9878	66	34	to	to	IN
9878	66	35	another	another	DT
9878	66	36	format	format	NN
9878	66	37	.	.	.
9878	67	1	They	-PRON-	PRP
9878	67	2	suggested	suggest	VBD
9878	67	3	that	that	IN
9878	67	4	action	action	NN
9878	67	5	is	be	VBZ
9878	67	6	needed	need	VBN
9878	67	7	to	to	TO
9878	67	8	ensure	ensure	VB
9878	67	9	proper	proper	JJ
9878	67	10	metadata	metadata	NN
9878	67	11	creation	creation	NN
9878	67	12	and	and	CC
9878	67	13	preservation	preservation	NN
9878	67	14	so	so	IN
9878	67	15	that	that	IN
9878	67	16	all	all	DT
9878	67	17	types	type	NNS
9878	67	18	of	of	IN
9878	67	19	metadata	metadata	NN
9878	67	20	must	must	MD
9878	67	21	be	be	VB
9878	67	22	captured	capture	VBN
9878	67	23	and	and	CC
9878	67	24	preserved	preserve	VBN
9878	67	25	to	to	TO
9878	67	26	achieve	achieve	VB
9878	67	27	the	the	DT
9878	67	28	most	most	RBS
9878	67	29	authentic	authentic	JJ
9878	67	30	,	,	,
9878	67	31	consistent	consistent	JJ
9878	67	32	,	,	,
9878	67	33	and	and	CC
9878	67	34	complete	complete	JJ
9878	67	35	digital	digital	JJ
9878	67	36	preservation	preservation	NN
9878	67	37	for	for	IN
9878	67	38	future	future	JJ
9878	67	39	use.8	use.8	CD
9878	67	40	Metadata	Metadata	NNP
9878	67	41	Extraction	Extraction	NNP
9878	67	42	Tools	Tools	NNPS
9878	67	43	and	and	CC
9878	67	44	Color	Color	NNP
9878	67	45	Profiles	Profiles	NNPS
9878	67	46	As	as	IN
9878	67	47	we	-PRON-	PRP
9878	67	48	digitize	digitize	VBP
9878	67	49	physical	physical	JJ
9878	67	50	documents	document	NNS
9878	67	51	and	and	CC
9878	67	52	manipulate	manipulate	NN
9878	67	53	images	image	NNS
9878	67	54	,	,	,
9878	67	55	color	color	NN
9878	67	56	management	management	NN
9878	67	57	is	be	VBZ
9878	67	58	important	important	JJ
9878	67	59	.	.	.
9878	68	1	The	the	DT
9878	68	2	goal	goal	NN
9878	68	3	of	of	IN
9878	68	4	color	color	NN
9878	68	5	management	management	NN
9878	68	6	is	be	VBZ
9878	68	7	to	to	TO
9878	68	8	obtain	obtain	VB
9878	68	9	a	a	DT
9878	68	10	controlled	control	VBN
9878	68	11	conversion	conversion	NN
9878	68	12	between	between	IN
9878	68	13	the	the	DT
9878	68	14	color	color	NN
9878	68	15	representations	representation	NNS
9878	68	16	of	of	IN
9878	68	17	various	various	JJ
9878	68	18	devices	device	NNS
9878	68	19	such	such	JJ
9878	68	20	as	as	IN
9878	68	21	image	image	NN
9878	68	22	scanners	scanner	NNS
9878	68	23	,	,	,
9878	68	24	digital	digital	JJ
9878	68	25	cameras	camera	NNS
9878	68	26	,	,	,
9878	68	27	and	and	CC
9878	68	28	monitors	monitor	NNS
9878	68	29	.	.	.
9878	69	1	A	a	DT
9878	69	2	color	color	NN
9878	69	3	profile	profile	NN
9878	69	4	is	be	VBZ
9878	69	5	a	a	DT
9878	69	6	set	set	NN
9878	69	7	of	of	IN
9878	69	8	data	datum	NNS
9878	69	9	that	that	WDT
9878	69	10	control	control	VBP
9878	69	11	input	input	NN
9878	69	12	and	and	CC
9878	69	13	output	output	NN
9878	69	14	of	of	IN
9878	69	15	a	a	DT
9878	69	16	color	color	NN
9878	69	17	space	space	NN
9878	69	18	.	.	.
9878	70	1	The	the	DT
9878	70	2	International	International	NNP
9878	70	3	Color	Color	NNP
9878	70	4	Consortium	Consortium	NNP
9878	70	5	(	(	-LRB-
9878	70	6	ICC	ICC	NNP
9878	70	7	)	)	-RRB-
9878	70	8	standards	standard	NNS
9878	70	9	and	and	CC
9878	70	10	profiles	profile	NNS
9878	70	11	were	be	VBD
9878	70	12	created	create	VBN
9878	70	13	to	to	TO
9878	70	14	bring	bring	VB
9878	70	15	various	various	JJ
9878	70	16	manufacturers	manufacturer	NNS
9878	70	17	together	together	RB
9878	70	18	because	because	IN
9878	70	19	embedding	embed	VBG
9878	70	20	color	color	NN
9878	70	21	profiles	profile	NNS
9878	70	22	into	into	IN
9878	70	23	images	image	NNS
9878	70	24	is	be	VBZ
9878	70	25	one	one	CD
9878	70	26	of	of	IN
9878	70	27	the	the	DT
9878	70	28	most	most	RBS
9878	70	29	important	important	JJ
9878	70	30	color	color	NN
9878	70	31	management	management	NN
9878	70	32	solutions	solution	NNS
9878	70	33	.	.	.
9878	71	1	Image	image	NN
9878	71	2	formats	format	NNS
9878	71	3	such	such	JJ
9878	71	4	as	as	IN
9878	71	5	TIFF	TIFF	NNP
9878	71	6	and	and	CC
9878	71	7	JPEG2000	JPEG2000	NNP
9878	71	8	and	and	CC
9878	71	9	document	document	NN
9878	71	10	formats	format	NNS
9878	71	11	such	such	JJ
9878	71	12	as	as	IN
9878	71	13	PDF	PDF	NNP
9878	71	14	may	may	MD
9878	71	15	contain	contain	VB
9878	71	16	embedded	embed	VBN
9878	71	17	color	color	NN
9878	71	18	profiles	profile	NNS
9878	71	19	.	.	.
9878	72	1	The	the	DT
9878	72	2	authors	author	NNS
9878	72	3	identified	identify	VBD
9878	72	4	a	a	DT
9878	72	5	few	few	JJ
9878	72	6	open	open	JJ
9878	72	7	source	source	NN
9878	72	8	tools	tool	NNS
9878	72	9	to	to	TO
9878	72	10	extract	extract	VB
9878	72	11	TIFF	TIFF	NNP
9878	72	12	metadata	metadata	NN
9878	72	13	,	,	,
9878	72	14	includin	includin	NNP
9878	72	15	g	g	NNP
9878	72	16	ExifTool	ExifTool	NNP
9878	72	17	,	,	,
9878	72	18	Exiv2	exiv2	NN
9878	72	19	,	,	,
9878	72	20	and	and	CC
9878	72	21	tiffInfo	tiffinfo	NN
9878	72	22	.	.	.
9878	73	1	ExifTool	ExifTool	NNP
9878	73	2	is	be	VBZ
9878	73	3	an	an	DT
9878	73	4	open	open	JJ
9878	73	5	source	source	NN
9878	73	6	tool	tool	NN
9878	73	7	for	for	IN
9878	73	8	reading	reading	NN
9878	73	9	,	,	,
9878	73	10	writing	writing	NN
9878	73	11	,	,	,
9878	73	12	and	and	CC
9878	73	13	manipulating	manipulate	VBG
9878	73	14	metadata	metadata	NN
9878	73	15	of	of	IN
9878	73	16	media	medium	NNS
9878	73	17	files	file	NNS
9878	73	18	.	.	.
9878	74	1	Exiv2	Exiv2	NNP
9878	74	2	is	be	VBZ
9878	74	3	another	another	DT
9878	74	4	free	free	JJ
9878	74	5	metadata	metadata	NN
9878	74	6	tool	tool	NN
9878	74	7	supporting	support	VBG
9878	74	8	different	different	JJ
9878	74	9	image	image	NN
9878	74	10	formats	format	NNS
9878	74	11	.	.	.
9878	75	1	The	the	DT
9878	75	2	tiffInfo	tiffinfo	NN
9878	75	3	program	program	NN
9878	75	4	is	be	VBZ
9878	75	5	widely	widely	RB
9878	75	6	used	use	VBN
9878	75	7	in	in	IN
9878	75	8	the	the	DT
9878	75	9	Linux	Linux	NNP
9878	75	10	platform	platform	NN
9878	75	11	,	,	,
9878	75	12	but	but	CC
9878	75	13	it	-PRON-	PRP
9878	75	14	has	have	VBZ
9878	75	15	not	not	RB
9878	75	16	been	be	VBN
9878	75	17	updated	update	VBN
9878	75	18	for	for	IN
9878	75	19	at	at	RB
9878	75	20	least	least	JJS
9878	75	21	ten	ten	CD
9878	75	22	years	year	NNS
9878	75	23	.	.	.
9878	76	1	Our	-PRON-	PRP$
9878	76	2	implementations	implementation	NNS
9878	76	3	showed	show	VBD
9878	76	4	that	that	IN
9878	76	5	ExifTool	ExifTool	NNP
9878	76	6	was	be	VBD
9878	76	7	the	the	DT
9878	76	8	one	one	NN
9878	76	9	that	that	WDT
9878	76	10	most	most	RBS
9878	76	11	easily	easily	RB
9878	76	12	extracted	extract	VBD
9878	76	13	the	the	DT
9878	76	14	full	full	JJ
9878	76	15	ICC	ICC	NNP
9878	76	16	profiles	profile	NNS
9878	76	17	and	and	CC
9878	76	18	other	other	JJ
9878	76	19	metadata	metadata	NN
9878	76	20	from	from	IN
9878	76	21	TIFF	TIFF	NNP
9878	76	22	and	and	CC
9878	76	23	JPEG2000	JPEG2000	NNP
9878	76	24	files	file	NNS
9878	76	25	.	.	.
9878	77	1	ImageMagick	ImageMagick	NNP
9878	77	2	and	and	CC
9878	77	3	other	other	JJ
9878	77	4	image	image	NN
9878	77	5	processing	processing	NN
9878	77	6	software	software	NN
9878	77	7	were	be	VBD
9878	77	8	examined	examine	VBN
9878	77	9	in	in	IN
9878	77	10	Van	Van	NNP
9878	77	11	der	der	NN
9878	77	12	Knijff	Knijff	NNP
9878	77	13	’s	’s	POS
9878	77	14	article	article	NN
9878	77	15	discussing	discuss	VBG
9878	77	16	JPEG2000	JPEG2000	NNP
9878	77	17	for	for	IN
9878	77	18	long	long	JJ
9878	77	19	-	-	HYPH
9878	77	20	term	term	NN
9878	77	21	preservation.9	preservation.9	NN
9878	77	22	He	-PRON-	PRP
9878	77	23	found	find	VBD
9878	77	24	that	that	IN
9878	77	25	ICC	ICC	NNP
9878	77	26	profiles	profile	NNS
9878	77	27	were	be	VBD
9878	77	28	lost	lose	VBN
9878	77	29	in	in	IN
9878	77	30	ImageMagick	ImageMagick	NNP
9878	77	31	.	.	.
9878	78	1	Our	-PRON-	PRP$
9878	78	2	implementation	implementation	NN
9878	78	3	has	have	VBZ
9878	78	4	INFORMATION	INFORMATION	VBN
9878	78	5	TECHNOLOGY	technology	NN
9878	78	6	AND	and	CC
9878	78	7	LIBRARIES	library	NNS
9878	78	8	|	|	NNP
9878	78	9	MARCH	MARCH	NNP
9878	78	10	2018	2018	CD
9878	78	11	56	56	CD
9878	78	12	showed	show	VBD
9878	78	13	the	the	DT
9878	78	14	current	current	JJ
9878	78	15	version	version	NN
9878	78	16	of	of	IN
9878	78	17	ImageMagick	ImageMagick	NNP
9878	78	18	has	have	VBZ
9878	78	19	fixed	fix	VBN
9878	78	20	this	this	DT
9878	78	21	issue	issue	NN
9878	78	22	.	.	.
9878	79	1	A	a	DT
9878	79	2	metadata	metadata	NN
9878	79	3	sample	sample	NN
9878	79	4	can	can	MD
9878	79	5	be	be	VB
9878	79	6	found	find	VBN
9878	79	7	in	in	IN
9878	79	8	appendix	appendix	NNP
9878	79	9	A.	A.	NNP
9878	80	1	IMPLEMENTATION	implementation	NN
9878	80	2	Converting	convert	VBG
9878	80	3	and	and	CC
9878	80	4	Ordering	ordering	NN
9878	80	5	TIFFs	TIFFs	NNPS
9878	80	6	into	into	IN
9878	80	7	a	a	DT
9878	80	8	Single	single	JJ
9878	80	9	PDF	PDF	NNP
9878	80	10	/	/	SYM
9878	80	11	A-2	A-2	NNP
9878	80	12	File	File	NNP
9878	80	13	When	when	WRB
9878	80	14	ordering	order	VBG
9878	80	15	and	and	CC
9878	80	16	combining	combine	VBG
9878	80	17	all	all	DT
9878	80	18	individual	individual	JJ
9878	80	19	TIFFs	TIFFs	NNPS
9878	80	20	of	of	IN
9878	80	21	a	a	DT
9878	80	22	document	document	NN
9878	80	23	into	into	IN
9878	80	24	a	a	DT
9878	80	25	single	single	JJ
9878	80	26	PDF	PDF	NNP
9878	80	27	/	/	SYM
9878	80	28	A-2b	A-2b	NNP
9878	80	29	file	file	NN
9878	80	30	,	,	,
9878	80	31	the	the	DT
9878	80	32	authors	author	NNS
9878	80	33	intended	intend	VBN
9878	80	34	to	to	TO
9878	80	35	preserve	preserve	VB
9878	80	36	all	all	DT
9878	80	37	information	information	NN
9878	80	38	from	from	IN
9878	80	39	the	the	DT
9878	80	40	TIFFs	TIFFs	NNPS
9878	80	41	,	,	,
9878	80	42	including	include	VBG
9878	80	43	raster	raster	NN
9878	80	44	image	image	NN
9878	80	45	data	datum	NNS
9878	80	46	streams	stream	NNS
9878	80	47	and	and	CC
9878	80	48	metadata	metadata	NN
9878	80	49	stored	store	VBN
9878	80	50	in	in	IN
9878	80	51	each	each	DT
9878	80	52	TIFF	TIFF	NNP
9878	80	53	’s	’s	POS
9878	80	54	header	header	NN
9878	80	55	.	.	.
9878	81	1	The	the	DT
9878	81	2	raster	raster	NN
9878	81	3	image	image	NN
9878	81	4	data	datum	NNS
9878	81	5	streams	stream	NNS
9878	81	6	are	be	VBP
9878	81	7	the	the	DT
9878	81	8	main	main	JJ
9878	81	9	images	image	NNS
9878	81	10	reflecting	reflect	VBG
9878	81	11	the	the	DT
9878	81	12	original	original	JJ
9878	81	13	look	look	NN
9878	81	14	and	and	CC
9878	81	15	feel	feel	VB
9878	81	16	of	of	IN
9878	81	17	these	these	DT
9878	81	18	pages	page	NNS
9878	81	19	,	,	,
9878	81	20	while	while	IN
9878	81	21	the	the	DT
9878	81	22	metadata	metadata	NN
9878	81	23	(	(	-LRB-
9878	81	24	including	include	VBG
9878	81	25	technical	technical	JJ
9878	81	26	and	and	CC
9878	81	27	administrative	administrative	JJ
9878	81	28	metadata	metadata	NN
9878	81	29	such	such	JJ
9878	81	30	as	as	IN
9878	81	31	BitsPerSample	bitspersample	RB
9878	81	32	,	,	,
9878	81	33	DateTime	DateTime	NNP
9878	81	34	,	,	,
9878	81	35	and	and	CC
9878	81	36	Make	make	VB
9878	81	37	/	/	SYM
9878	81	38	Model	Model	NNP
9878	81	39	/	/	SYM
9878	81	40	Software	Software	NNP
9878	81	41	)	)	-RRB-
9878	81	42	tells	tell	VBZ
9878	81	43	us	-PRON-	PRP
9878	81	44	important	important	JJ
9878	81	45	digitization	digitization	NN
9878	81	46	and	and	CC
9878	81	47	provenance	provenance	NN
9878	81	48	information	information	NN
9878	81	49	.	.	.
9878	82	1	Both	both	DT
9878	82	2	are	be	VBP
9878	82	3	critical	critical	JJ
9878	82	4	for	for	IN
9878	82	5	delivery	delivery	NN
9878	82	6	and	and	CC
9878	82	7	digital	digital	JJ
9878	82	8	preservation	preservation	NN
9878	82	9	.	.	.
9878	83	1	The	the	DT
9878	83	2	TIFF	TIFF	NNP
9878	83	3	images	image	NNS
9878	83	4	were	be	VBD
9878	83	5	first	first	RB
9878	83	6	converted	convert	VBN
9878	83	7	to	to	IN
9878	83	8	JPEG2000	JPEG2000	NNP
9878	83	9	with	with	IN
9878	83	10	lossless	lossless	JJ
9878	83	11	compression	compression	NN
9878	83	12	using	use	VBG
9878	83	13	the	the	DT
9878	83	14	open	open	JJ
9878	83	15	source	source	NN
9878	83	16	ImageMagick	ImageMagick	NNP
9878	83	17	software	software	NN
9878	83	18	.	.	.
9878	84	1	Our	-PRON-	PRP$
9878	84	2	tests	test	NNS
9878	84	3	of	of	IN
9878	84	4	ImageMagick	ImageMagick	NNP
9878	84	5	demonstrated	demonstrate	VBD
9878	84	6	that	that	IN
9878	84	7	it	-PRON-	PRP
9878	84	8	can	can	MD
9878	84	9	handle	handle	VB
9878	84	10	different	different	JJ
9878	84	11	color	color	NN
9878	84	12	profiles	profile	NNS
9878	84	13	and	and	CC
9878	84	14	will	will	MD
9878	84	15	convert	convert	VB
9878	84	16	images	image	NNS
9878	84	17	correctly	correctly	RB
9878	84	18	if	if	IN
9878	84	19	the	the	DT
9878	84	20	original	original	JJ
9878	84	21	TIFF	TIFF	NNP
9878	84	22	comes	come	VBZ
9878	84	23	with	with	IN
9878	84	24	a	a	DT
9878	84	25	color	color	NN
9878	84	26	profile	profile	NN
9878	84	27	.	.	.
9878	85	1	This	this	DT
9878	85	2	gave	give	VBD
9878	85	3	us	-PRON-	PRP
9878	85	4	confidence	confidence	NN
9878	85	5	that	that	IN
9878	85	6	past	past	JJ
9878	85	7	concerns	concern	NNS
9878	85	8	about	about	IN
9878	85	9	JPEG2000	JPEG2000	NNP
9878	85	10	and	and	CC
9878	85	11	ImageMagick	ImageMagick	NNP
9878	85	12	had	have	VBD
9878	85	13	been	be	VBN
9878	85	14	resolved	resolve	VBN
9878	85	15	.	.	.
9878	86	1	These	these	DT
9878	86	2	images	image	NNS
9878	86	3	were	be	VBD
9878	86	4	then	then	RB
9878	86	5	properly	properly	RB
9878	86	6	sorted	sort	VBN
9878	86	7	into	into	IN
9878	86	8	their	-PRON-	PRP$
9878	86	9	original	original	JJ
9878	86	10	order	order	NN
9878	86	11	and	and	CC
9878	86	12	combined	combine	VBN
9878	86	13	into	into	IN
9878	86	14	a	a	DT
9878	86	15	single	single	JJ
9878	86	16	PDF	PDF	NNP
9878	86	17	/	/	SYM
9878	86	18	A-2	A-2	NNP
9878	86	19	file	file	NN
9878	86	20	.	.	.
9878	87	1	An	an	DT
9878	87	2	alternative	alternative	NN
9878	87	3	is	be	VBZ
9878	87	4	to	to	TO
9878	87	5	directly	directly	RB
9878	87	6	code	code	VB
9878	87	7	TIFF	TIFF	NNP
9878	87	8	’s	’s	POS
9878	87	9	image	image	NN
9878	87	10	data	datum	NNS
9878	87	11	stream	stream	NN
9878	87	12	into	into	IN
9878	87	13	a	a	DT
9878	87	14	PDF	pdf	NN
9878	87	15	/	/	,
9878	87	16	A	a	DT
9878	87	17	file	file	NN
9878	87	18	,	,	,
9878	87	19	but	but	CC
9878	87	20	this	this	DT
9878	87	21	approach	approach	NN
9878	87	22	would	would	MD
9878	87	23	miss	miss	VB
9878	87	24	one	one	CD
9878	87	25	benefit	benefit	NN
9878	87	26	of	of	IN
9878	87	27	PDF	PDF	NNP
9878	87	28	/	/	SYM
9878	87	29	A-2	A-2	NNP
9878	87	30	:	:	:
9878	87	31	tremendous	tremendous	JJ
9878	87	32	file	file	NN
9878	87	33	size	size	NN
9878	87	34	reduction	reduction	NN
9878	87	35	with	with	IN
9878	87	36	JPEG2000	JPEG2000	NNP
9878	87	37	.	.	.
9878	88	1	The	the	DT
9878	88	2	following	follow	VBG
9878	88	3	is	be	VBZ
9878	88	4	the	the	DT
9878	88	5	pseudocode	pseudocode	NN
9878	88	6	of	of	IN
9878	88	7	ordering	ordering	NN
9878	88	8	and	and	CC
9878	88	9	combining	combine	VBG
9878	88	10	all	all	PDT
9878	88	11	the	the	DT
9878	88	12	TIFFs	TIFFs	NNPS
9878	88	13	in	in	IN
9878	88	14	a	a	DT
9878	88	15	text	text	NN
9878	88	16	document	document	NN
9878	88	17	into	into	IN
9878	88	18	a	a	DT
9878	88	19	single	single	JJ
9878	88	20	PDF	pdf	NN
9878	88	21	/	/	SYM
9878	88	22	A-	a-	NN
9878	88	23	2	2	CD
9878	88	24	file	file	NN
9878	88	25	.	.	.
9878	89	1	CreatePDFA2(queue	CreatePDFA2(queue	NNP
9878	89	2	TiffList	TiffList	NNP
9878	89	3	)	)	-RRB-
9878	89	4	{	{	-LRB-
9878	89	5	Create	create	VB
9878	89	6	an	an	DT
9878	89	7	empty	empty	JJ
9878	89	8	queue	queue	NN
9878	89	9	XMLQ	XMLQ	NNP
9878	89	10	;	;	:
9878	89	11	Create	create	VB
9878	89	12	an	an	DT
9878	89	13	empty	empty	JJ
9878	89	14	queue	queue	NN
9878	89	15	JP2Q	jp2q	NN
9878	89	16	;	;	:
9878	89	17	/	/	NFP
9878	89	18	*	*	NFP
9878	89	19	TiffFileList	tifffilelist	NN
9878	89	20	is	be	VBZ
9878	89	21	pre	pre	JJ
9878	89	22	-	-	JJ
9878	89	23	sorted	sorted	JJ
9878	89	24	queue	queue	NN
9878	89	25	based	base	VBN
9878	89	26	on	on	IN
9878	89	27	the	the	DT
9878	89	28	original	original	JJ
9878	89	29	order	order	NN
9878	89	30	*	*	NFP
9878	89	31	/	/	SYM
9878	89	32	/	/	SYM
9878	89	33	*	*	NFP
9878	89	34	Convert	convert	VB
9878	89	35	each	each	DT
9878	89	36	TIFF	TIFF	NNP
9878	89	37	to	to	IN
9878	89	38	JPEG2000	JPEG2000	NNP
9878	89	39	losslessly	losslessly	RB
9878	89	40	,	,	,
9878	89	41	then	then	RB
9878	89	42	add	add	VB
9878	89	43	each	each	DT
9878	89	44	JPEG2000	JPEG2000	NNP
9878	89	45	and	and	CC
9878	89	46	its	-PRON-	PRP$
9878	89	47	metadata	metadata	NN
9878	89	48	into	into	IN
9878	89	49	a	a	DT
9878	89	50	queue	queue	NN
9878	89	51	*	*	NFP
9878	89	52	/	/	SYM
9878	89	53	while	while	IN
9878	89	54	(	(	-LRB-
9878	89	55	TiffList	TiffList	NNP
9878	89	56	is	be	VBZ
9878	89	57	NOT	not	RB
9878	89	58	empty	empty	JJ
9878	89	59	)	)	-RRB-
9878	89	60	{	{	-LRB-
9878	89	61	String	String	NNP
9878	89	62	TiffFilePath	TiffFilePath	NNP
9878	89	63	=	=	NFP
9878	89	64	TiffList.dequeue	TiffList.dequeue	NNP
9878	89	65	(	(	-LRB-
9878	89	66	)	)	-RRB-
9878	89	67	;	;	:
9878	89	68	string	stre	VBG
9878	89	69	xmlFilePath	xmlfilepath	NN
9878	89	70	=	=	NFP
9878	89	71	Tiff	Tiff	NNP
9878	89	72	metadata	metadata	NN
9878	89	73	extracted	extract	VBD
9878	89	74	using	use	VBG
9878	89	75	exiftool	exiftool	NN
9878	89	76	;	;	:
9878	89	77	XMLQ.enqueue(xmlFilePath	XMLQ.enqueue(xmlFilePath	NNP
9878	89	78	)	)	-RRB-
9878	89	79	;	;	:
9878	89	80	String	string	NN
9878	89	81	jp2FilePath	jp2filepath	NN
9878	89	82	=	=	SYM
9878	89	83	JPEG2000	JPEG2000	NNP
9878	89	84	file	file	NN
9878	89	85	location	location	NN
9878	89	86	from	from	IN
9878	89	87	Tiff	Tiff	NNP
9878	89	88	converted	convert	VBN
9878	89	89	by	by	IN
9878	89	90	ImageMagick	ImageMagick	NNP
9878	89	91	;	;	:
9878	89	92	JP2Q.enqueue(jp2FilePath	JP2Q.enqueue(jp2FilePath	NNP
9878	89	93	)	)	-RRB-
9878	89	94	;	;	:
9878	89	95	}	}	-RRB-
9878	89	96	/	/	NFP
9878	89	97	*	*	NFP
9878	89	98	Convert	convert	VB
9878	89	99	each	each	DT
9878	89	100	image	image	NN
9878	89	101	’s	’s	POS
9878	89	102	metadata	metadata	NN
9878	89	103	to	to	IN
9878	89	104	XMP	XMP	NNP
9878	89	105	,	,	,
9878	89	106	add	add	VB
9878	89	107	each	each	DT
9878	89	108	JPEG2000	JPEG2000	NNP
9878	89	109	and	and	CC
9878	89	110	its	-PRON-	PRP$
9878	89	111	metadata	metadata	NN
9878	89	112	into	into	IN
9878	89	113	the	the	DT
9878	89	114	PDF	PDF	NNP
9878	89	115	/	/	SYM
9878	89	116	A-2	A-2	NNP
9878	89	117	file	file	NN
9878	89	118	based	base	VBN
9878	89	119	on	on	IN
9878	89	120	its	-PRON-	PRP$
9878	89	121	original	original	JJ
9878	89	122	order	order	NN
9878	89	123	*	*	NFP
9878	89	124	/	/	,
9878	89	125	Document	document	NN
9878	89	126	pdf2b	pdf2b	''
9878	89	127	=	=	:
9878	89	128	new	new	JJ
9878	89	129	Document	document	NN
9878	89	130	(	(	-LRB-
9878	89	131	)	)	-RRB-
9878	89	132	;	;	:
9878	89	133	/	/	NFP
9878	89	134	*	*	NFP
9878	89	135	create	create	VBP
9878	89	136	PDF	PDF	NNP
9878	89	137	/	/	SYM
9878	89	138	A-2b	A-2b	NNP
9878	89	139	conformance	conformance	NN
9878	89	140	level	level	NN
9878	89	141	*	*	NFP
9878	89	142	/	/	SYM
9878	89	143	PdfAWriter	pdfawriter	NN
9878	89	144	writer	writer	NN
9878	89	145	=	=	SYM
9878	89	146	PdfAWriter.getInstance(doc	PdfAWriter.getInstance(doc	NNP
9878	89	147	,	,	,
9878	89	148	new	new	NNP
9878	89	149	FileOutputStream(PdfAFilePath),PdfAConformaceLevel	FileOutputStream(PdfAFilePath),PdfAConformaceLevel	.
9878	89	150	.	.	.
9878	89	151	PDF_A_2B	PDF_A_2B	NNP
9878	89	152	)	)	-RRB-
9878	89	153	;	;	:
9878	89	154	writer.createXmpMetadata	writer.createXmpMetadata	NNP
9878	89	155	(	(	-LRB-
9878	89	156	)	)	-RRB-
9878	89	157	;	;	:
9878	89	158	//Create	//Create	NFP
9878	89	159	Root	Root	NNP
9878	89	160	XMP	XMP	NNP
9878	89	161	DIGITIZATION	DIGITIZATION	NNS
9878	89	162	OF	of	IN
9878	89	163	TEXT	text	NN
9878	89	164	DOCUMENTS	documents	NN
9878	89	165	USING	USING	NNP
9878	89	166	PDF	PDF	NNP
9878	89	167	/	/	SYM
9878	89	168	A	A	NNP
9878	89	169	|	|	NNP
9878	89	170	HAN	HAN	NNP
9878	89	171	AND	and	CC
9878	89	172	WAN	WAN	NNP
9878	89	173	57	57	CD
9878	89	174	HTTPS://DOI.ORG/10.6017	HTTPS://DOI.ORG/10.6017	NNS
9878	89	175	/	/	SYM
9878	89	176	ITAL.V37I1.9878	ITAL.V37I1.9878	NNP
9878	89	177	pdf2b.open	pdf2b.open	NN
9878	89	178	(	(	-LRB-
9878	89	179	)	)	-RRB-
9878	89	180	;	;	:
9878	89	181	while(JP2Q	while(JP2Q	NNP
9878	89	182	is	be	VBZ
9878	89	183	NOT	not	RB
9878	89	184	empty	empty	JJ
9878	89	185	)	)	-RRB-
9878	89	186	{	{	-LRB-
9878	89	187	Image	image	NN
9878	89	188	jp2	jp2	NN
9878	89	189	=	=	-RRB-
9878	89	190	Image.getInstance(JP2Q.dequeue	Image.getInstance(JP2Q.dequeue	NNP
9878	89	191	(	(	-LRB-
9878	89	192	)	)	-RRB-
9878	89	193	)	)	-RRB-
9878	89	194	;	;	:
9878	89	195	Rectangle	Rectangle	NNP
9878	89	196	size	size	NN
9878	89	197	=	=	SYM
9878	89	198	new	new	JJ
9878	89	199	Rectangle(jp2.getWidth	Rectangle(jp2.getWidth	NNP
9878	89	200	(	(	-LRB-
9878	89	201	)	)	-RRB-
9878	89	202	,	,	,
9878	89	203	jp2.getHeight	jp2.getHeight	NNP
9878	89	204	(	(	-LRB-
9878	89	205	)	)	-RRB-
9878	89	206	)	)	-RRB-
9878	89	207	;	;	:
9878	89	208	//PDF	//PDF	.
9878	89	209	page	page	NN
9878	89	210	size	size	NN
9878	89	211	setting	set	VBG
9878	89	212	pdf2b.setPageSize(size	pdf2b.setpagesize(size	NN
9878	89	213	)	)	-RRB-
9878	89	214	;	;	:
9878	89	215	pdf2b.newPage	pdf2b.newpage	NN
9878	89	216	(	(	-LRB-
9878	89	217	)	)	-RRB-
9878	89	218	;	;	:
9878	89	219	//	//	SYM
9878	89	220	create	create	VBP
9878	89	221	a	a	DT
9878	89	222	new	new	JJ
9878	89	223	page	page	NN
9878	89	224	for	for	IN
9878	89	225	a	a	DT
9878	89	226	new	new	JJ
9878	89	227	image	image	NN
9878	89	228	byte	byte	NN
9878	89	229	[	[	-LRB-
9878	89	230	]	]	-RRB-
9878	89	231	bytearr	bytearr	NNP
9878	89	232	=	=	NFP
9878	89	233	XmpManipulation(XMLQ.dequeue	XmpManipulation(XMLQ.dequeue	NNP
9878	89	234	(	(	-LRB-
9878	89	235	)	)	-RRB-
9878	89	236	)	)	-RRB-
9878	89	237	;	;	:
9878	89	238	//	//	SYM
9878	89	239	convert	convert	VB
9878	89	240	original	original	JJ
9878	89	241	metadata	metadata	NN
9878	89	242	based	base	VBN
9878	89	243	on	on	IN
9878	89	244	the	the	DT
9878	89	245	XMP	XMP	NNP
9878	89	246	standard	standard	NN
9878	89	247	writer	writer	NN
9878	89	248	.setPageXmpMetadata(bytearr	.setPageXmpMetadata(bytearr	.
9878	89	249	)	)	-RRB-
9878	89	250	;	;	:
9878	89	251	pdf2b.add(jp2	pdf2b.add(jp2	NNP
9878	89	252	)	)	-RRB-
9878	89	253	;	;	:
9878	89	254	}	}	-RRB-
9878	89	255	pdf2b.close	pdf2b.close	NN
9878	89	256	(	(	-LRB-
9878	89	257	)	)	-RRB-
9878	89	258	;	;	:
9878	89	259	}	}	-RRB-
9878	89	260	Converting	convert	VBG
9878	89	261	PDF	PDF	NNP
9878	89	262	/	/	SYM
9878	89	263	A-2	A-2	NNP
9878	89	264	Files	file	VBZ
9878	89	265	back	back	RB
9878	89	266	to	to	IN
9878	89	267	TIFFs	TIFFs	NNPS
9878	89	268	and	and	CC
9878	89	269	JPEG2000s	jpeg2000s	$
9878	89	270	To	to	TO
9878	89	271	ensure	ensure	VB
9878	89	272	that	that	IN
9878	89	273	we	-PRON-	PRP
9878	89	274	can	can	MD
9878	89	275	extract	extract	VB
9878	89	276	raster	raster	NN
9878	89	277	images	image	NNS
9878	89	278	from	from	IN
9878	89	279	the	the	DT
9878	89	280	newly	newly	RB
9878	89	281	created	create	VBN
9878	89	282	PDF	PDF	NNP
9878	89	283	/	/	SYM
9878	89	284	A-2	A-2	NNP
9878	89	285	file	file	NN
9878	89	286	,	,	,
9878	89	287	the	the	DT
9878	89	288	authors	author	NNS
9878	89	289	also	also	RB
9878	89	290	wrote	write	VBD
9878	89	291	code	code	NN
9878	89	292	to	to	TO
9878	89	293	convert	convert	VB
9878	89	294	a	a	DT
9878	89	295	PDF	PDF	NNP
9878	89	296	/	/	SYM
9878	89	297	A-2	A-2	NNP
9878	89	298	file	file	NN
9878	89	299	back	back	RB
9878	89	300	to	to	IN
9878	89	301	the	the	DT
9878	89	302	original	original	JJ
9878	89	303	TIFF	TIFF	NNP
9878	89	304	or	or	CC
9878	89	305	JPEG2000	JPEG2000	NNP
9878	89	306	format	format	NN
9878	89	307	.	.	.
9878	90	1	This	this	DT
9878	90	2	implementation	implementation	NN
9878	90	3	was	be	VBD
9878	90	4	a	a	DT
9878	90	5	reverse	reverse	JJ
9878	90	6	process	process	NN
9878	90	7	of	of	IN
9878	90	8	the	the	DT
9878	90	9	above	above	JJ
9878	90	10	operation	operation	NN
9878	90	11	.	.	.
9878	91	1	Once	once	IN
9878	91	2	the	the	DT
9878	91	3	reverse	reverse	JJ
9878	91	4	conversion	conversion	NN
9878	91	5	process	process	NN
9878	91	6	was	be	VBD
9878	91	7	completed	complete	VBN
9878	91	8	,	,	,
9878	91	9	the	the	DT
9878	91	10	authors	author	NNS
9878	91	11	verified	verify	VBD
9878	91	12	that	that	IN
9878	91	13	the	the	DT
9878	91	14	image	image	NN
9878	91	15	files	file	NNS
9878	91	16	created	create	VBN
9878	91	17	from	from	IN
9878	91	18	the	the	DT
9878	91	19	PDF	PDF	NNP
9878	91	20	/	/	SYM
9878	91	21	A-2	A-2	NNP
9878	91	22	file	file	NN
9878	91	23	were	be	VBD
9878	91	24	the	the	DT
9878	91	25	same	same	JJ
9878	91	26	as	as	IN
9878	91	27	before	before	IN
9878	91	28	the	the	DT
9878	91	29	conversion	conversion	NN
9878	91	30	to	to	IN
9878	91	31	PDF	PDF	NNP
9878	91	32	/	/	SYM
9878	91	33	A-2	A-2	NNP
9878	91	34	.	.	.
9878	92	1	Note	note	VB
9878	92	2	that	that	IN
9878	92	3	we	-PRON-	PRP
9878	92	4	generated	generate	VBD
9878	92	5	MD5	MD5	NNP
9878	92	6	checksums	checksum	NNS
9878	92	7	to	to	TO
9878	92	8	verify	verify	VB
9878	92	9	image	image	NN
9878	92	10	data	datum	NNS
9878	92	11	streams	stream	NNS
9878	92	12	.	.	.
9878	93	1	Images	image	NNS
9878	93	2	data	datum	NNS
9878	93	3	streams	stream	NNS
9878	93	4	are	be	VBP
9878	93	5	the	the	DT
9878	93	6	same	same	JJ
9878	93	7	,	,	,
9878	93	8	but	but	CC
9878	93	9	metadata	metadata	NN
9878	93	10	location	location	NN
9878	93	11	can	can	MD
9878	93	12	be	be	VB
9878	93	13	varied	varied	JJ
9878	93	14	because	because	IN
9878	93	15	of	of	IN
9878	93	16	inconsistent	inconsistent	JJ
9878	93	17	TIFF	TIFF	NNP
9878	93	18	tags	tag	NNS
9878	93	19	used	use	VBN
9878	93	20	over	over	IN
9878	93	21	the	the	DT
9878	93	22	years	year	NNS
9878	93	23	.	.	.
9878	94	1	When	when	WRB
9878	94	2	converting	convert	VBG
9878	94	3	one	one	CD
9878	94	4	TIFF	TIFF	NNP
9878	94	5	to	to	IN
9878	94	6	another	another	DT
9878	94	7	TIFF	TIFF	NNP
9878	94	8	,	,	,
9878	94	9	ImageMagick	ImageMagick	NNP
9878	94	10	has	have	VBZ
9878	94	11	its	-PRON-	PRP$
9878	94	12	implementation	implementation	NN
9878	94	13	of	of	IN
9878	94	14	metadata	metadata	NN
9878	94	15	tags	tag	NNS
9878	94	16	.	.	.
9878	95	1	The	the	DT
9878	95	2	code	code	NN
9878	95	3	can	can	MD
9878	95	4	be	be	VB
9878	95	5	found	find	VBN
9878	95	6	in	in	IN
9878	95	7	appendix	appendix	NNP
9878	95	8	B.	B.	NNP
9878	95	9	PDF	PDF	NNP
9878	95	10	/	/	,
9878	95	11	A	A	NNP
9878	95	12	Validation	validation	NN
9878	95	13	PDF	pdf	NN
9878	95	14	/	/	SYM
9878	95	15	A	A	NNP
9878	95	16	is	be	VBZ
9878	95	17	one	one	CD
9878	95	18	of	of	IN
9878	95	19	the	the	DT
9878	95	20	most	most	RBS
9878	95	21	recognized	recognize	VBN
9878	95	22	digital	digital	JJ
9878	95	23	preservation	preservation	NN
9878	95	24	formats	format	NNS
9878	95	25	,	,	,
9878	95	26	specially	specially	RB
9878	95	27	designed	design	VBN
9878	95	28	for	for	IN
9878	95	29	long	long	JJ
9878	95	30	-term	-term	HYPH
9878	95	31	preservation	preservation	NN
9878	95	32	and	and	CC
9878	95	33	access	access	NN
9878	95	34	.	.	.
9878	96	1	However	however	RB
9878	96	2	,	,	,
9878	96	3	no	no	DT
9878	96	4	commonly	commonly	RB
9878	96	5	accepted	accept	VBN
9878	96	6	PDF	PDF	NNP
9878	96	7	/	/	,
9878	96	8	A	a	DT
9878	96	9	validator	validator	NN
9878	96	10	was	be	VBD
9878	96	11	available	available	JJ
9878	96	12	in	in	IN
9878	96	13	the	the	DT
9878	96	14	past	past	NN
9878	96	15	,	,	,
9878	96	16	although	although	IN
9878	96	17	several	several	JJ
9878	96	18	commercial	commercial	JJ
9878	96	19	and	and	CC
9878	96	20	open	open	JJ
9878	96	21	source	source	NN
9878	96	22	PDF	PDF	NNP
9878	96	23	preflight	preflight	NN
9878	96	24	and	and	CC
9878	96	25	validation	validation	NN
9878	96	26	engines	engine	NNS
9878	96	27	(	(	-LRB-
9878	96	28	e.g.	e.g.	RB
9878	96	29	,	,	,
9878	96	30	Acrobat	Acrobat	NNP
9878	96	31	)	)	-RRB-
9878	96	32	were	be	VBD
9878	96	33	available	available	JJ
9878	96	34	.	.	.
9878	97	1	Validating	validate	VBG
9878	97	2	a	a	DT
9878	97	3	PDF	pdf	NN
9878	97	4	/	/	SYM
9878	97	5	A	a	NN
9878	97	6	against	against	IN
9878	97	7	the	the	DT
9878	97	8	PDF	PDF	NNP
9878	97	9	/	/	SYM
9878	97	10	A	a	DT
9878	97	11	standards	standard	NNS
9878	97	12	is	be	VBZ
9878	97	13	a	a	DT
9878	97	14	challenging	challenging	JJ
9878	97	15	task	task	NN
9878	97	16	for	for	IN
9878	97	17	a	a	DT
9878	97	18	few	few	JJ
9878	97	19	reasons	reason	NNS
9878	97	20	,	,	,
9878	97	21	including	include	VBG
9878	97	22	the	the	DT
9878	97	23	complexity	complexity	NN
9878	97	24	of	of	IN
9878	97	25	the	the	DT
9878	97	26	PDF	PDF	NNP
9878	97	27	and	and	CC
9878	97	28	PDF	PDF	NNP
9878	97	29	/	/	SYM
9878	97	30	A	A	NNP
9878	97	31	formats	format	NNS
9878	97	32	.	.	.
9878	98	1	The	the	DT
9878	98	2	PDF	PDF	NNP
9878	98	3	Association	Association	NNP
9878	98	4	and	and	CC
9878	98	5	the	the	DT
9878	98	6	Open	Open	NNP
9878	98	7	Preservation	Preservation	NNP
9878	98	8	Foundation	Foundation	NNP
9878	98	9	recognized	recognize	VBD
9878	98	10	the	the	DT
9878	98	11	need	need	NN
9878	98	12	and	and	CC
9878	98	13	started	start	VBD
9878	98	14	a	a	DT
9878	98	15	project	project	NN
9878	98	16	to	to	TO
9878	98	17	develop	develop	VB
9878	98	18	an	an	DT
9878	98	19	open	open	JJ
9878	98	20	source	source	NN
9878	98	21	PDF	PDF	NNP
9878	98	22	/	/	,
9878	98	23	A	a	DT
9878	98	24	validator	validator	NN
9878	98	25	and	and	CC
9878	98	26	build	build	VB
9878	98	27	a	a	DT
9878	98	28	maintenance	maintenance	NN
9878	98	29	community	community	NN
9878	98	30	.	.	.
9878	99	1	Their	-PRON-	PRP$
9878	99	2	result	result	NN
9878	99	3	,	,	,
9878	99	4	VeraPDF	verapdf	FW
9878	99	5	,	,	,
9878	99	6	is	be	VBZ
9878	99	7	an	an	DT
9878	99	8	open	open	JJ
9878	99	9	source	source	NN
9878	99	10	validator	validator	NN
9878	99	11	designed	design	VBN
9878	99	12	for	for	IN
9878	99	13	all	all	DT
9878	99	14	PDF	PDF	NNP
9878	99	15	/	/	SYM
9878	99	16	A	a	DT
9878	99	17	parts	part	NNS
9878	99	18	and	and	CC
9878	99	19	conformance	conformance	NN
9878	99	20	levels	level	NNS
9878	99	21	.	.	.
9878	100	1	Released	release	VBN
9878	100	2	in	in	IN
9878	100	3	January	January	NNP
9878	100	4	2017	2017	CD
9878	100	5	,	,	,
9878	100	6	the	the	DT
9878	100	7	goal	goal	NN
9878	100	8	of	of	IN
9878	100	9	veraPDF	veraPDF	NNP
9878	100	10	is	be	VBZ
9878	100	11	to	to	TO
9878	100	12	become	become	VB
9878	100	13	the	the	DT
9878	100	14	commonly	commonly	RB
9878	100	15	accepted	accept	VBN
9878	100	16	PDF	PDF	NNP
9878	100	17	/	/	,
9878	100	18	A	A	NNP
9878	100	19	validator	validator	NN
9878	100	20	.	.	.
9878	101	1	10	10	CD
9878	101	2	Our	-PRON-	PRP$
9878	101	3	generated	generate	VBN
9878	101	4	PDF	PDF	NNP
9878	101	5	/	/	SYM
9878	101	6	As	as	IN
9878	101	7	have	have	VBP
9878	101	8	been	be	VBN
9878	101	9	validated	validate	VBN
9878	101	10	with	with	IN
9878	101	11	veraPDF	veraPDF	NNP
9878	101	12	1.4	1.4	CD
9878	101	13	and	and	CC
9878	101	14	Adobe	Adobe	NNP
9878	101	15	Acrobat	Acrobat	NNP
9878	101	16	Pro	Pro	NNP
9878	101	17	DC	DC	NNP
9878	101	18	Preflight	Preflight	NNP
9878	101	19	.	.	.
9878	102	1	Both	both	DT
9878	102	2	products	product	NNS
9878	102	3	validated	validate	VBD
9878	102	4	the	the	DT
9878	102	5	PDF	PDF	NNP
9878	102	6	/	/	SYM
9878	102	7	A-2b	A-2b	NNP
9878	102	8	files	file	NNS
9878	102	9	as	as	IN
9878	102	10	fully	fully	RB
9878	102	11	compatible	compatible	JJ
9878	102	12	.	.	.
9878	103	1	Our	-PRON-	PRP$
9878	103	2	implementations	implementation	NNS
9878	103	3	showed	show	VBD
9878	103	4	that	that	IN
9878	103	5	veraPDF	veraPDF	NNP
9878	103	6	1.4	1.4	CD
9878	103	7	verified	verify	VBD
9878	103	8	more	more	JJR
9878	103	9	cases	case	NNS
9878	103	10	than	than	IN
9878	103	11	Acrobat	Acrobat	NNP
9878	103	12	DC	DC	NNP
9878	103	13	Preflight	Preflight	NNP
9878	103	14	.	.	.
9878	104	1	Figure	figure	NN
9878	104	2	1	1	CD
9878	104	3	shows	show	VBZ
9878	104	4	a	a	DT
9878	104	5	PDF	PDF	NNP
9878	104	6	file	file	NN
9878	104	7	structure	structure	NN
9878	104	8	and	and	CC
9878	104	9	its	-PRON-	PRP$
9878	104	10	metadata	metadata	NN
9878	104	11	.	.	.
9878	105	1	INFORMATION	INFORMATION	NNP
9878	105	2	TECHNOLOGY	technology	NN
9878	105	3	AND	and	CC
9878	105	4	LIBRARIES	library	NNS
9878	105	5	|	|	NNP
9878	105	6	MARCH	MARCH	NNP
9878	105	7	2018	2018	CD
9878	105	8	58	58	CD
9878	105	9	Figure	figure	NN
9878	105	10	1	1	CD
9878	105	11	.	.	.
9878	106	1	A	a	DT
9878	106	2	PDF	PDF	NNP
9878	106	3	object	object	NN
9878	106	4	tree	tree	NN
9878	106	5	with	with	IN
9878	106	6	root	root	NN
9878	106	7	-	-	HYPH
9878	106	8	level	level	NN
9878	106	9	metadata	metadata	NN
9878	106	10	.	.	.
9878	107	1	RUNTIME	RUNTIME	NNP
9878	107	2	AND	and	CC
9878	107	3	CONCLUSION	conclusion	VB
9878	107	4	The	the	DT
9878	107	5	time	time	NN
9878	107	6	complexity	complexity	NN
9878	107	7	of	of	IN
9878	107	8	our	-PRON-	PRP$
9878	107	9	code	code	NN
9878	107	10	is	be	VBZ
9878	107	11	O(log	O(log	NNP
9878	107	12	n	n	NNP
9878	107	13	)	)	-RRB-
9878	107	14	because	because	IN
9878	107	15	of	of	IN
9878	107	16	the	the	DT
9878	107	17	sorting	sort	VBG
9878	107	18	algorithms	algorithm	NNS
9878	107	19	used	use	VBD
9878	107	20	.	.	.
9878	108	1	TIFFs	tiff	NNS
9878	108	2	were	be	VBD
9878	108	3	first	first	RB
9878	108	4	converted	convert	VBN
9878	108	5	to	to	IN
9878	108	6	JPEG2000	JPEG2000	NNP
9878	108	7	.	.	.
9878	109	1	When	when	WRB
9878	109	2	JPEG2000	JPEG2000	NNP
9878	109	3	images	image	NNS
9878	109	4	are	be	VBP
9878	109	5	added	add	VBN
9878	109	6	to	to	IN
9878	109	7	a	a	DT
9878	109	8	PDF	PDF	NNP
9878	109	9	/	/	SYM
9878	109	10	A-2	A-2	NNP
9878	109	11	file	file	NN
9878	109	12	,	,	,
9878	109	13	no	no	DT
9878	109	14	further	further	JJ
9878	109	15	image	image	NN
9878	109	16	manipulation	manipulation	NN
9878	109	17	is	be	VBZ
9878	109	18	required	require	VBN
9878	109	19	because	because	IN
9878	109	20	the	the	DT
9878	109	21	generated	generate	VBN
9878	109	22	PDF	PDF	NNP
9878	109	23	/	/	SYM
9878	109	24	A-2	A-2	NNP
9878	109	25	uses	use	VBZ
9878	109	26	JPEG2000	JPEG2000	NNP
9878	109	27	directly	directly	RB
9878	109	28	(	(	-LRB-
9878	109	29	in	in	IN
9878	109	30	other	other	JJ
9878	109	31	words	word	NNS
9878	109	32	,	,	,
9878	109	33	it	-PRON-	PRP
9878	109	34	uses	use	VBZ
9878	109	35	the	the	DT
9878	109	36	JPXDecode	JPXDecode	NNP
9878	109	37	filter	filter	NN
9878	109	38	)	)	-RRB-
9878	109	39	.	.	.
9878	110	1	Tables	table	NNS
9878	110	2	1	1	CD
9878	110	3	and	and	CC
9878	110	4	2	2	CD
9878	110	5	show	show	VB
9878	110	6	the	the	DT
9878	110	7	performance	performance	NN
9878	110	8	comparison	comparison	NN
9878	110	9	running	run	VBG
9878	110	10	in	in	IN
9878	110	11	our	-PRON-	PRP$
9878	110	12	computer	computer	NN
9878	110	13	hardware	hardware	NN
9878	110	14	and	and	CC
9878	110	15	software	software	NN
9878	110	16	environment	environment	NN
9878	110	17	(	(	-LRB-
9878	110	18	Intel	Intel	NNP
9878	110	19	Core	Core	NNP
9878	110	20	i7	i7	NN
9878	110	21	-	-	HYPH
9878	110	22	2600	2600	CD
9878	110	23	CPU@3.4GHz	CPU@3.4GHz	NNP
9878	110	24	,	,	,
9878	110	25	8	8	CD
9878	110	26	GB	GB	NNP
9878	110	27	DDR3	DDR3	NNP
9878	110	28	RAM	RAM	NNP
9878	110	29	,	,	,
9878	110	30	3	3	CD
9878	110	31	TB	TB	NNP
9878	110	32	7200-RPM	7200-RPM	VBG
9878	110	33	64MB	64mb	CD
9878	110	34	-	-	HYPH
9878	110	35	cache	cache	JJ
9878	110	36	hard	hard	JJ
9878	110	37	disk	disk	NN
9878	110	38	running	run	VBG
9878	110	39	Ubuntu	Ubuntu	NNP
9878	110	40	16.10	16.10	CD
9878	110	41	)	)	-RRB-
9878	110	42	.	.	.
9878	111	1	DIGITIZATION	DIGITIZATION	NNS
9878	111	2	OF	of	IN
9878	111	3	TEXT	text	NN
9878	111	4	DOCUMENTS	documents	NN
9878	111	5	USING	USING	NNP
9878	111	6	PDF	PDF	NNP
9878	111	7	/	/	SYM
9878	111	8	A	A	NNP
9878	111	9	|	|	NNP
9878	111	10	HAN	HAN	NNP
9878	111	11	AND	and	CC
9878	111	12	WAN	WAN	NNP
9878	111	13	59	59	CD
9878	111	14	HTTPS://DOI.ORG/10.6017	HTTPS://DOI.ORG/10.6017	NNS
9878	111	15	/	/	SYM
9878	111	16	ITAL.V37I1.9878	ITAL.V37I1.9878	NNP
9878	111	17	Table	table	NN
9878	111	18	1	1	CD
9878	111	19	.	.	.
9878	112	1	Runtimes	runtime	NNS
9878	112	2	of	of	IN
9878	112	3	converting	convert	VBG
9878	112	4	grayscale	grayscale	JJ
9878	112	5	TIFFs	TIFFs	NNPS
9878	112	6	to	to	IN
9878	112	7	JPEG2000s	JPEG2000s	NNP
9878	112	8	and	and	CC
9878	112	9	to	to	IN
9878	112	10	PDF	PDF	NNP
9878	112	11	/	/	SYM
9878	112	12	A-2b	A-2b	NNP
9878	112	13	No	no	NN
9878	112	14	.	.	.
9878	113	1	of	of	IN
9878	113	2	Files	Files	NNP
9878	113	3	Total	Total	NNP
9878	113	4	File	file	NN
9878	113	5	Size	size	NN
9878	113	6	(	(	-LRB-
9878	113	7	MB	MB	NNP
9878	113	8	)	)	-RRB-
9878	113	9	Image	Image	NNP
9878	113	10	Conversion	Conversion	NNP
9878	113	11	Runtime	Runtime	NNP
9878	113	12	(	(	-LRB-
9878	113	13	TIFFs	TIFFs	NNP
9878	113	14	to	to	IN
9878	113	15	JP2s	JP2s	NNP
9878	113	16	in	in	IN
9878	113	17	seconds	second	NNS
9878	113	18	)	)	-RRB-
9878	113	19	Total	Total	NNP
9878	113	20	Runtime	Runtime	NNP
9878	113	21	(	(	-LRB-
9878	113	22	TIFFs	tiff	VBN
9878	113	23	to	to	IN
9878	113	24	JP2s	JP2s	NNP
9878	113	25	to	to	IN
9878	113	26	a	a	DT
9878	113	27	single	single	JJ
9878	113	28	PDF	PDF	NNP
9878	113	29	/	/	SYM
9878	113	30	A-2b	A-2b	NNP
9878	113	31	in	in	IN
9878	113	32	seconds	second	NNS
9878	113	33	)	)	-RRB-
9878	113	34	1	1	CD
9878	113	35	9.1	9.1	CD
9878	113	36	3.61	3.61	CD
9878	113	37	3.98	3.98	CD
9878	113	38	10	10	CD
9878	113	39	91.1	91.1	CD
9878	113	40	35.63	35.63	CD
9878	113	41	36.71	36.71	CD
9878	113	42	20	20	CD
9878	113	43	182.2	182.2	CD
9878	113	44	71.83	71.83	CD
9878	113	45	73.98	73.98	CD
9878	113	46	50	50	CD
9878	113	47	455.5	455.5	CD
9878	113	48	179.06	179.06	CD
9878	113	49	184.63	184.63	CD
9878	113	50	100	100	CD
9878	113	51	910.9	910.9	CD
9878	113	52	358.3	358.3	CD
9878	113	53	370.91	370.91	CD
9878	113	54	Table	Table	NNP
9878	113	55	2	2	CD
9878	113	56	.	.	.
9878	114	1	Runtimes	runtime	NNS
9878	114	2	of	of	IN
9878	114	3	converting	convert	VBG
9878	114	4	color	color	NN
9878	114	5	TIFFs	TIFFs	NNPS
9878	114	6	to	to	IN
9878	114	7	JPEG2000s	JPEG2000s	NNP
9878	114	8	and	and	CC
9878	114	9	to	to	IN
9878	114	10	PDF	PDF	NNP
9878	114	11	/	/	SYM
9878	114	12	A-2b	A-2b	NNP
9878	114	13	No	no	NN
9878	114	14	.	.	.
9878	115	1	of	of	IN
9878	115	2	Files	Files	NNP
9878	115	3	Total	Total	NNP
9878	115	4	File	file	NN
9878	115	5	Size	size	NN
9878	115	6	(	(	-LRB-
9878	115	7	MB	MB	NNP
9878	115	8	)	)	-RRB-
9878	115	9	Image	Image	NNP
9878	115	10	Conversion	Conversion	NNP
9878	115	11	Runtime	Runtime	NNP
9878	115	12	(	(	-LRB-
9878	115	13	TIFFs	TIFFs	NNP
9878	115	14	to	to	IN
9878	115	15	JP2s	JP2s	NNP
9878	115	16	in	in	IN
9878	115	17	seconds	second	NNS
9878	115	18	)	)	-RRB-
9878	115	19	Total	Total	NNP
9878	115	20	Runtime	Runtime	NNP
9878	115	21	(	(	-LRB-
9878	115	22	TIFFs	tiff	VBN
9878	115	23	to	to	IN
9878	115	24	JP2s	JP2s	NNP
9878	115	25	to	to	IN
9878	115	26	a	a	DT
9878	115	27	single	single	JJ
9878	115	28	PDF	PDF	NNP
9878	115	29	/	/	SYM
9878	115	30	A-2b	A-2b	NNP
9878	115	31	in	in	IN
9878	115	32	seconds	second	NNS
9878	115	33	)	)	-RRB-
9878	115	34	1	1	CD
9878	115	35	27.3	27.3	CD
9878	115	36	14.80	14.80	CD
9878	115	37	14.94	14.94	CD
9878	115	38	10	10	CD
9878	115	39	273	273	CD
9878	115	40	150.51	150.51	CD
9878	115	41	151.55	151.55	CD
9878	115	42	20	20	CD
9878	115	43	546	546	CD
9878	115	44	289.95	289.95	CD
9878	115	45	293.21	293.21	CD
9878	115	46	50	50	CD
9878	115	47	1,415	1,415	CD
9878	115	48	741.89	741.89	CD
9878	115	49	749.75	749.75	CD
9878	115	50	100	100	CD
9878	115	51	2,730	2,730	CD
9878	115	52	1490.49	1490.49	CD
9878	115	53	1509.23	1509.23	CD
9878	115	54	The	the	DT
9878	115	55	results	result	NNS
9878	115	56	show	show	VBP
9878	115	57	that	that	WDT
9878	115	58	(	(	-LRB-
9878	115	59	a	a	LS
9878	115	60	)	)	-RRB-
9878	115	61	the	the	DT
9878	115	62	majority	majority	NN
9878	115	63	of	of	IN
9878	115	64	the	the	DT
9878	115	65	runtime	runtime	NN
9878	115	66	(	(	-LRB-
9878	115	67	more	more	JJR
9878	115	68	than	than	IN
9878	115	69	95	95	CD
9878	115	70	percent	percent	NN
9878	115	71	)	)	-RRB-
9878	115	72	is	be	VBZ
9878	115	73	spent	spend	VBN
9878	115	74	in	in	IN
9878	115	75	converting	convert	VBG
9878	115	76	a	a	DT
9878	115	77	TIFF	TIFF	NNP
9878	115	78	to	to	IN
9878	115	79	a	a	DT
9878	115	80	JPEG2000	JPEG2000	NNP
9878	115	81	using	use	VBG
9878	115	82	ImageMagick	ImageMagick	NNP
9878	115	83	(	(	-LRB-
9878	115	84	see	see	VB
9878	115	85	figure	figure	NN
9878	115	86	2	2	CD
9878	115	87	)	)	-RRB-
9878	115	88	;	;	:
9878	115	89	(	(	-LRB-
9878	115	90	b	b	LS
9878	115	91	)	)	-RRB-
9878	115	92	the	the	DT
9878	115	93	average	average	JJ
9878	115	94	runtime	runtime	NN
9878	115	95	of	of	IN
9878	115	96	converting	convert	VBG
9878	115	97	a	a	DT
9878	115	98	TIFF	TIFF	NNP
9878	115	99	has	have	VBZ
9878	115	100	a	a	DT
9878	115	101	constant	constant	JJ
9878	115	102	positive	positive	JJ
9878	115	103	relationship	relationship	NN
9878	115	104	with	with	IN
9878	115	105	the	the	DT
9878	115	106	file	file	NN
9878	115	107	’s	’s	POS
9878	115	108	size	size	NN
9878	115	109	(	(	-LRB-
9878	115	110	see	see	VB
9878	115	111	figure	figure	NN
9878	115	112	2	2	CD
9878	115	113	)	)	-RRB-
9878	115	114	;	;	:
9878	115	115	(	(	-LRB-
9878	115	116	c	c	NN
9878	115	117	)	)	-RRB-
9878	115	118	in	in	IN
9878	115	119	INFORMATION	INFORMATION	NNP
9878	115	120	TECHNOLOGY	TECHNOLOGY	NNP
9878	115	121	AND	and	CC
9878	115	122	LIBRARIES	library	NNS
9878	115	123	|	|	NNP
9878	115	124	MARCH	MARCH	NNP
9878	115	125	2018	2018	CD
9878	115	126	60	60	CD
9878	115	127	comparison	comparison	NN
9878	115	128	,	,	,
9878	115	129	the	the	DT
9878	115	130	runtime	runtime	NN
9878	115	131	of	of	IN
9878	115	132	converting	convert	VBG
9878	115	133	a	a	DT
9878	115	134	color	color	NN
9878	115	135	TIFF	TIFF	NNP
9878	115	136	is	be	VBZ
9878	115	137	significantly	significantly	RB
9878	115	138	higher	high	JJR
9878	115	139	than	than	IN
9878	115	140	that	that	DT
9878	115	141	of	of	IN
9878	115	142	converting	convert	VBG
9878	115	143	a	a	DT
9878	115	144	greyscale	greyscale	JJ
9878	115	145	TIFF	TIFF	NNP
9878	115	146	(	(	-LRB-
9878	115	147	see	see	VB
9878	115	148	figure	figure	NN
9878	115	149	2	2	CD
9878	115	150	)	)	-RRB-
9878	115	151	;	;	:
9878	115	152	and	and	CC
9878	115	153	(	(	-LRB-
9878	115	154	d	d	NN
9878	115	155	)	)	-RRB-
9878	115	156	it	-PRON-	PRP
9878	115	157	is	be	VBZ
9878	115	158	feasible	feasible	JJ
9878	115	159	in	in	IN
9878	115	160	terms	term	NNS
9878	115	161	of	of	IN
9878	115	162	time	time	NN
9878	115	163	and	and	CC
9878	115	164	resources	resource	NNS
9878	115	165	to	to	TO
9878	115	166	convert	convert	VB
9878	115	167	existing	exist	VBG
9878	115	168	master	master	NN
9878	115	169	images	image	NNS
9878	115	170	of	of	IN
9878	115	171	digital	digital	JJ
9878	115	172	document	document	NN
9878	115	173	collections	collection	NNS
9878	115	174	to	to	IN
9878	115	175	PDF	PDF	NNP
9878	115	176	/	/	SYM
9878	115	177	A-2b	A-2b	NNP
9878	115	178	.	.	.
9878	116	1	For	for	IN
9878	116	2	example	example	NN
9878	116	3	,	,	,
9878	116	4	the	the	DT
9878	116	5	runtime	runtime	NN
9878	116	6	of	of	IN
9878	116	7	1	1	CD
9878	116	8	TB	tb	NN
9878	116	9	of	of	IN
9878	116	10	conversion	conversion	NN
9878	116	11	of	of	IN
9878	116	12	color	color	NN
9878	116	13	TIFFs	TIFFs	NNPS
9878	116	14	will	will	MD
9878	116	15	be	be	VB
9878	116	16	552,831	552,831	CD
9878	116	17	seconds	second	NNS
9878	116	18	(	(	-LRB-
9878	116	19	153.5	153.5	CD
9878	116	20	hours	hour	NNS
9878	116	21	;	;	:
9878	116	22	6.398	6.398	CD
9878	116	23	days	day	NNS
9878	116	24	)	)	-RRB-
9878	116	25	using	use	VBG
9878	116	26	the	the	DT
9878	116	27	above	above	JJ
9878	116	28	hardware	hardware	NN
9878	116	29	.	.	.
9878	117	1	The	the	DT
9878	117	2	authors	author	NNS
9878	117	3	have	have	VBP
9878	117	4	already	already	RB
9878	117	5	processed	process	VBN
9878	117	6	more	more	JJR
9878	117	7	than	than	IN
9878	117	8	600,000	600,000	CD
9878	117	9	TIFFs	tiff	NNS
9878	117	10	using	use	VBG
9878	117	11	this	this	DT
9878	117	12	method	method	NN
9878	117	13	.	.	.
9878	118	1	The	the	DT
9878	118	2	authors	author	NNS
9878	118	3	conclude	conclude	VBP
9878	118	4	that	that	IN
9878	118	5	using	use	VBG
9878	118	6	PDF	PDF	NNP
9878	118	7	/	/	,
9878	118	8	A	A	NNP
9878	118	9	gives	give	VBZ
9878	118	10	institutions	institution	NNS
9878	118	11	advantages	advantage	NNS
9878	118	12	of	of	IN
9878	118	13	the	the	DT
9878	118	14	newly	newly	RB
9878	118	15	preferred	prefer	VBN
9878	118	16	master	master	NN
9878	118	17	file	file	NN
9878	118	18	format	format	NN
9878	118	19	for	for	IN
9878	118	20	digitization	digitization	NN
9878	118	21	of	of	IN
9878	118	22	text	text	NN
9878	118	23	documents	document	NNS
9878	118	24	over	over	IN
9878	118	25	TIFF	TIFF	NNP
9878	118	26	/	/	SYM
9878	118	27	JPEG2000	JPEG2000	NNP
9878	118	28	.	.	.
9878	119	1	The	the	DT
9878	119	2	above	above	JJ
9878	119	3	implementation	implementation	NN
9878	119	4	demonstrates	demonstrate	VBZ
9878	119	5	the	the	DT
9878	119	6	ease	ease	NN
9878	119	7	,	,	,
9878	119	8	the	the	DT
9878	119	9	reasonable	reasonable	JJ
9878	119	10	runtime	runtime	NN
9878	119	11	,	,	,
9878	119	12	and	and	CC
9878	119	13	the	the	DT
9878	119	14	availability	availability	NN
9878	119	15	of	of	IN
9878	119	16	open	open	JJ
9878	119	17	source	source	NN
9878	119	18	software	software	NN
9878	119	19	to	to	TO
9878	119	20	perform	perform	VB
9878	119	21	such	such	JJ
9878	119	22	conversions	conversion	NNS
9878	119	23	.	.	.
9878	120	1	From	from	IN
9878	120	2	both	both	CC
9878	120	3	the	the	DT
9878	120	4	theoretical	theoretical	JJ
9878	120	5	analysis	analysis	NN
9878	120	6	and	and	CC
9878	120	7	empirical	empirical	JJ
9878	120	8	evidences	evidence	NNS
9878	120	9	,	,	,
9878	120	10	the	the	DT
9878	120	11	authors	author	NNS
9878	120	12	show	show	VBP
9878	120	13	that	that	IN
9878	120	14	PDF	PDF	NNP
9878	120	15	/	/	SYM
9878	120	16	A	A	NNP
9878	120	17	has	have	VBZ
9878	120	18	advantages	advantage	NNS
9878	120	19	over	over	IN
9878	120	20	the	the	DT
9878	120	21	traditional	traditional	JJ
9878	120	22	preferred	preferred	JJ
9878	120	23	file	file	NN
9878	120	24	format	format	NN
9878	120	25	TIFF	TIFF	NNP
9878	120	26	for	for	IN
9878	120	27	digitization	digitization	NN
9878	120	28	of	of	IN
9878	120	29	text	text	NN
9878	120	30	documents	document	NNS
9878	120	31	.	.	.
9878	121	1	Following	follow	VBG
9878	121	2	best	good	JJS
9878	121	3	practice	practice	NN
9878	121	4	,	,	,
9878	121	5	a	a	DT
9878	121	6	PDF	PDF	NNP
9878	121	7	/	/	SYM
9878	121	8	A	a	DT
9878	121	9	file	file	NN
9878	121	10	can	can	MD
9878	121	11	be	be	VB
9878	121	12	a	a	DT
9878	121	13	self-	self-	NN
9878	121	14	contained	contain	VBN
9878	121	15	and	and	CC
9878	121	16	self	self	NN
9878	121	17	-	-	HYPH
9878	121	18	described	describe	VBN
9878	121	19	container	container	NN
9878	121	20	that	that	WDT
9878	121	21	accommodates	accommodate	VBZ
9878	121	22	all	all	PDT
9878	121	23	the	the	DT
9878	121	24	data	datum	NNS
9878	121	25	from	from	IN
9878	121	26	digitization	digitization	NN
9878	121	27	of	of	IN
9878	121	28	textual	textual	JJ
9878	121	29	materials	material	NNS
9878	121	30	,	,	,
9878	121	31	including	include	VBG
9878	121	32	page	page	NN
9878	121	33	-	-	HYPH
9878	121	34	level	level	NN
9878	121	35	metadata	metadata	NN
9878	121	36	and	and	CC
9878	121	37	ICC	icc	NN
9878	121	38	profiles	profile	NNS
9878	121	39	.	.	.
9878	122	1	SUMMARY	summary	VB
9878	122	2	The	the	DT
9878	122	3	goal	goal	NN
9878	122	4	of	of	IN
9878	122	5	this	this	DT
9878	122	6	article	article	NN
9878	122	7	is	be	VBZ
9878	122	8	to	to	TO
9878	122	9	demonstrate	demonstrate	VB
9878	122	10	empirical	empirical	JJ
9878	122	11	evidences	evidence	NNS
9878	122	12	of	of	IN
9878	122	13	using	use	VBG
9878	122	14	PDF	PDF	NNP
9878	122	15	/	/	,
9878	122	16	A	A	NNP
9878	122	17	for	for	IN
9878	122	18	digitization	digitization	NN
9878	122	19	of	of	IN
9878	122	20	text	text	NN
9878	122	21	document	document	NN
9878	122	22	.	.	.
9878	123	1	The	the	DT
9878	123	2	authors	author	NNS
9878	123	3	evaluated	evaluate	VBD
9878	123	4	and	and	CC
9878	123	5	used	use	VBN
9878	123	6	multiple	multiple	JJ
9878	123	7	open	open	JJ
9878	123	8	source	source	NN
9878	123	9	software	software	NN
9878	123	10	programs	program	NNS
9878	123	11	for	for	IN
9878	123	12	processing	process	VBG
9878	123	13	raster	raster	NN
9878	123	14	images	image	NNS
9878	123	15	,	,	,
9878	123	16	extracting	extract	VBG
9878	123	17	image	image	NN
9878	123	18	metadata	metadata	NN
9878	123	19	,	,	,
9878	123	20	and	and	CC
9878	123	21	generating	generate	VBG
9878	123	22	PDF	PDF	NNP
9878	123	23	/	/	,
9878	123	24	A	a	DT
9878	123	25	files	file	NNS
9878	123	26	.	.	.
9878	124	1	These	these	DT
9878	124	2	PDF	PDF	NNP
9878	124	3	/	/	,
9878	124	4	A	a	DT
9878	124	5	files	file	NNS
9878	124	6	were	be	VBD
9878	124	7	validated	validate	VBN
9878	124	8	using	use	VBG
9878	124	9	the	the	DT
9878	124	10	up	up	RB
9878	124	11	-	-	HYPH
9878	124	12	to	to	IN
9878	124	13	-	-	HYPH
9878	124	14	date	date	NN
9878	124	15	PDF	PDF	NNP
9878	124	16	/	/	SYM
9878	124	17	A	A	NNP
9878	124	18	validators	validator	NNS
9878	124	19	veraPDF	veraPDF	NNP
9878	124	20	and	and	CC
9878	124	21	Acrobat	Acrobat	NNP
9878	124	22	Preflight	Preflight	NNP
9878	124	23	.	.	.
9878	125	1	The	the	DT
9878	125	2	authors	author	NNS
9878	125	3	also	also	RB
9878	125	4	calculated	calculate	VBD
9878	125	5	the	the	DT
9878	125	6	time	time	NN
9878	125	7	complexity	complexity	NN
9878	125	8	of	of	IN
9878	125	9	the	the	DT
9878	125	10	program	program	NN
9878	125	11	and	and	CC
9878	125	12	measured	measure	VBD
9878	125	13	the	the	DT
9878	125	14	total	total	JJ
9878	125	15	runtime	runtime	NN
9878	125	16	in	in	IN
9878	125	17	multiple	multiple	JJ
9878	125	18	testing	testing	NN
9878	125	19	cases	case	NNS
9878	125	20	.	.	.
9878	126	1	Most	Most	JJS
9878	126	2	of	of	IN
9878	126	3	the	the	DT
9878	126	4	runtime	runtime	NN
9878	126	5	was	be	VBD
9878	126	6	spent	spend	VBN
9878	126	7	on	on	IN
9878	126	8	image	image	NN
9878	126	9	conversions	conversion	NNS
9878	126	10	from	from	IN
9878	126	11	TIFF	TIFF	NNP
9878	126	12	to	to	IN
9878	126	13	JPEG2000	JPEG2000	NNP
9878	126	14	.	.	.
9878	127	1	The	the	DT
9878	127	2	creation	creation	NN
9878	127	3	of	of	IN
9878	127	4	the	the	DT
9878	127	5	PDF	PDF	NNP
9878	127	6	/	/	SYM
9878	127	7	A-2b	A-2b	NNP
9878	127	8	file	file	NN
9878	127	9	with	with	IN
9878	127	10	associated	associate	VBN
9878	127	11	page	page	NN
9878	127	12	-	-	HYPH
9878	127	13	level	level	NN
9878	127	14	metadata	metadata	NN
9878	127	15	accounted	account	VBD
9878	127	16	for	for	IN
9878	127	17	less	less	JJR
9878	127	18	than	than	IN
9878	127	19	5	5	CD
9878	127	20	percent	percent	NN
9878	127	21	of	of	IN
9878	127	22	the	the	DT
9878	127	23	total	total	JJ
9878	127	24	runtime	runtime	NN
9878	127	25	.	.	.
9878	128	1	Runtime	runtime	NN
9878	128	2	of	of	IN
9878	128	3	conversion	conversion	NN
9878	128	4	of	of	IN
9878	128	5	a	a	DT
9878	128	6	color	color	NN
9878	128	7	TIFF	TIFF	NNP
9878	128	8	was	be	VBD
9878	128	9	much	much	RB
9878	128	10	higher	high	JJR
9878	128	11	than	than	IN
9878	128	12	that	that	DT
9878	128	13	of	of	IN
9878	128	14	a	a	DT
9878	128	15	greyscale	greyscale	JJ
9878	128	16	one	one	NN
9878	128	17	.	.	.
9878	129	1	Our	-PRON-	PRP$
9878	129	2	theoretical	theoretical	JJ
9878	129	3	analysis	analysis	NN
9878	129	4	and	and	CC
9878	129	5	empirical	empirical	JJ
9878	129	6	examples	example	NNS
9878	129	7	show	show	VBP
9878	129	8	that	that	IN
9878	129	9	using	use	VBG
9878	129	10	PDF	PDF	NNP
9878	129	11	/	/	SYM
9878	129	12	A-2	A-2	NNP
9878	129	13	presents	present	VBZ
9878	129	14	many	many	JJ
9878	129	15	advantages	advantage	NNS
9878	129	16	over	over	IN
9878	129	17	the	the	DT
9878	129	18	traditional	traditional	JJ
9878	129	19	preferred	preferred	JJ
9878	129	20	file	file	NN
9878	129	21	format	format	NN
9878	129	22	(	(	-LRB-
9878	129	23	TIFF	TIFF	NNP
9878	129	24	/	/	SYM
9878	129	25	JPEG2000	JPEG2000	NNP
9878	129	26	)	)	-RRB-
9878	129	27	for	for	IN
9878	129	28	digitization	digitization	NN
9878	129	29	of	of	IN
9878	129	30	text	text	NN
9878	129	31	documents	document	NNS
9878	129	32	.	.	.
9878	130	1	DIGITIZATION	DIGITIZATION	NNS
9878	130	2	OF	of	IN
9878	130	3	TEXT	text	NN
9878	130	4	DOCUMENTS	documents	NN
9878	130	5	USING	USING	NNP
9878	130	6	PDF	PDF	NNP
9878	130	7	/	/	SYM
9878	130	8	A	A	NNP
9878	130	9	|	|	NNP
9878	130	10	HAN	HAN	NNP
9878	130	11	AND	and	CC
9878	130	12	WAN	WAN	NNP
9878	130	13	61	61	CD
9878	130	14	HTTPS://DOI.ORG/10.6017	HTTPS://DOI.ORG/10.6017	NNS
9878	130	15	/	/	SYM
9878	130	16	ITAL.V37I1.9878	ital.v37i1.9878	JJ
9878	130	17	Figure	figure	NN
9878	130	18	2	2	CD
9878	130	19	.	.	.
9878	131	1	File	file	NN
9878	131	2	size	size	NN
9878	131	3	,	,	,
9878	131	4	greyscale	greyscale	NN
9878	131	5	and	and	CC
9878	131	6	color	color	NN
9878	131	7	TIFFs	tiff	NNS
9878	131	8	and	and	CC
9878	131	9	runtime	runtime	NN
9878	131	10	ratio	ratio	NN
9878	131	11	.	.	.
9878	132	1	INFORMATION	INFORMATION	NNP
9878	132	2	TECHNOLOGY	technology	NN
9878	132	3	AND	and	CC
9878	132	4	LIBRARIES	library	NNS
9878	132	5	|	|	NNP
9878	132	6	MARCH	MARCH	NNP
9878	132	7	2018	2018	CD
9878	132	8	62	62	CD
9878	132	9	APPENDIX	APPENDIX	NNP
9878	132	10	A	a	DT
9878	132	11	:	:	:
9878	132	12	SAMPLE	SAMPLE	NNP
9878	132	13	TIFF	TIFF	NNP
9878	132	14	METADATA	metadata	VBP
9878	132	15	WITH	with	IN
9878	132	16	ICC	icc	NN
9878	132	17	HEADER	HEADER	NNS
9878	132	18	<	<	XX
9878	132	19	tiff	tiff	NN
9878	132	20	:	:	:
9878	132	21	BitsPerSample>8</tiff	bitspersample>8</tiff	NN
9878	132	22	:	:	:
9878	132	23	BitsPerSample	BitsPerSample	NNP
9878	132	24	>	>	XX
9878	132	25	<	<	XX
9878	132	26	IFD0	ifd0	NN
9878	132	27	:	:	:
9878	132	28	ImageWidth>3400</IFD0	ImageWidth>3400</IFD0	NNP
9878	132	29	:	:	:
9878	132	30	ImageWidth	ImageWidth	NNP
9878	132	31	>	>	XX
9878	132	32	<	<	XX
9878	132	33	IFD0	IFD0	NNP
9878	132	34	:	:	:
9878	132	35	ImageHeight>4680</IFD0	ImageHeight>4680</IFD0	NNP
9878	132	36	:	:	:
9878	132	37	ImageHeight	ImageHeight	NNP
9878	132	38	>	>	XX
9878	132	39	<	<	XX
9878	132	40	IFD0	IFD0	NNP
9878	132	41	:	:	:
9878	132	42	BitsPerSample>8	BitsPerSample>8	NNP
9878	132	43	8	8	CD
9878	132	44	8</IFD0	8</ifd0	CD
9878	132	45	:	:	:
9878	132	46	BitsPerSample	BitsPerSample	NNP
9878	132	47	>	>	XX
9878	132	48	<	<	XX
9878	132	49	IFD0	IFD0	NNP
9878	132	50	:	:	:
9878	132	51	Compression	compression	NN
9878	132	52	>	>	XX
9878	132	53	Uncompressed</IFD0	uncompressed</ifd0	CD
9878	132	54	:	:	:
9878	132	55	Compression	compression	NN
9878	132	56	>	>	XX
9878	132	57	<	<	XX
9878	132	58	IFD0	IFD0	NNP
9878	132	59	:	:	:
9878	132	60	PhotometricInterpretation	PhotometricInterpretation	NNP
9878	132	61	>	>	XX
9878	132	62	RGB</IFD0	rgb</ifd0	XX
9878	132	63	:	:	:
9878	132	64	PhotometricInterpretation	PhotometricInterpretation	NNP
9878	132	65	>	>	XX
9878	132	66	<	<	XX
9878	132	67	IFD0	ifd0	XX
9878	132	68	:	:	:
9878	132	69	StripOffsets>(Binary	stripoffsets>(binary	JJ
9878	132	70	data	datum	NNS
9878	132	71	41025	41025	CD
9878	132	72	bytes	byte	NNS
9878	132	73	,	,	,
9878	132	74	use	use	NN
9878	132	75	-b	-b	HYPH
9878	132	76	option	option	NN
9878	132	77	to	to	IN
9878	132	78	extract)</IFD0	extract)</IFD0	NNP
9878	132	79	:	:	:
9878	132	80	StripOffsets	StripOffsets	NNP
9878	132	81	>	>	XX
9878	132	82	<	<	XX
9878	132	83	IFD0	IFD0	NNP
9878	132	84	:	:	:
9878	132	85	SamplesPerPixel>3</IFD0	samplesperpixel>3</ifd0	NN
9878	132	86	:	:	:
9878	132	87	SamplesPerPixel	SamplesPerPixel	NNP
9878	132	88	>	>	XX
9878	132	89	<	<	XX
9878	132	90	IFD0	IFD0	NNP
9878	132	91	:	:	:
9878	132	92	RowsPerStrip>1</IFD0	rowsperstrip>1</ifd0	IN
9878	132	93	:	:	:
9878	132	94	RowsPerStrip	RowsPerStrip	NNP
9878	132	95	>	>	XX
9878	132	96	<	<	XX
9878	132	97	IFD0	IFD0	NNP
9878	132	98	:	:	:
9878	132	99	StripByteCounts>(Binary	StripByteCounts>(Binary	NNP
9878	132	100	data	datum	NNS
9878	132	101	28079	28079	CD
9878	132	102	bytes	byte	NNS
9878	132	103	,	,	,
9878	132	104	use	use	NN
9878	132	105	-b	-b	HYPH
9878	132	106	option	option	NN
9878	132	107	to	to	IN
9878	132	108	extract)</IFD0	extract)</IFD0	NNP
9878	132	109	:	:	:
9878	132	110	StripByteCounts	stripbytecount	NNS
9878	132	111	>	>	XX
9878	132	112	<	<	XX
9878	132	113	IFD0	IFD0	NNP
9878	132	114	:	:	:
9878	132	115	XResolution>400</IFD0	XResolution>400</IFD0	NNP
9878	132	116	:	:	:
9878	132	117	XResolution	xresolution	NN
9878	132	118	>	>	XX
9878	132	119	<	<	XX
9878	132	120	IFD0	ifd0	NN
9878	132	121	:	:	:
9878	132	122	YResolution>400</IFD0	yresolution>400</ifd0	NN
9878	132	123	:	:	:
9878	132	124	YResolution	yresolution	NN
9878	132	125	>	>	XX
9878	132	126	<	<	XX
9878	132	127	IFD0	IFD0	NNP
9878	132	128	:	:	:
9878	132	129	PlanarConfiguration	PlanarConfiguration	NNP
9878	132	130	>	>	XX
9878	132	131	Chunky</IFD0	chunky</ifd0	XX
9878	132	132	:	:	:
9878	132	133	PlanarConfiguration	PlanarConfiguration	NNP
9878	132	134	>	>	XX
9878	132	135	<	<	XX
9878	132	136	ICC	ICC	NNP
9878	132	137	-	-	HYPH
9878	132	138	header	header	NN
9878	132	139	:	:	:
9878	132	140	ProfileCMMType	profilecmmtype	NN
9878	132	141	>	>	FW
9878	132	142	APPL</ICC	APPL</ICC	NNP
9878	132	143	-	-	HYPH
9878	132	144	header	header	NN
9878	132	145	:	:	:
9878	132	146	ProfileCMMType	profilecmmtype	NN
9878	132	147	>	>	XX
9878	132	148	<	<	XX
9878	132	149	ICC	ICC	NNP
9878	132	150	-	-	HYPH
9878	132	151	header	header	NNP
9878	132	152	:	:	:
9878	132	153	ProfileVersion>2.2.0</ICC	profileversion>2.2.0</icc	NN
9878	132	154	-	-	HYPH
9878	132	155	header	header	NN
9878	132	156	:	:	:
9878	132	157	ProfileVersion	ProfileVersion	NNP
9878	132	158	>	>	XX
9878	132	159	<	<	XX
9878	132	160	ICC	ICC	NNP
9878	132	161	-	-	HYPH
9878	132	162	header	header	NN
9878	132	163	:	:	:
9878	132	164	ProfileClass	ProfileClass	NNP
9878	132	165	>	>	NN
9878	132	166	Display	Display	NNP
9878	132	167	Device	Device	NNP
9878	132	168	Profile</ICC	Profile</ICC	NNP
9878	132	169	-	-	HYPH
9878	132	170	header	header	NN
9878	132	171	:	:	:
9878	132	172	ProfileClass	ProfileClass	NNP
9878	132	173	>	>	XX
9878	132	174	<	<	XX
9878	132	175	ICC	ICC	NNP
9878	132	176	-	-	HYPH
9878	132	177	header	header	NNP
9878	132	178	:	:	:
9878	132	179	ColorSpaceData	ColorSpaceData	NNP
9878	132	180	>	>	XX
9878	132	181	RGB	RGB	NNP
9878	132	182	<	<	XX
9878	132	183	/ICC	/ICC	NNP
9878	132	184	-	-	HYPH
9878	132	185	header	header	NN
9878	132	186	:	:	:
9878	132	187	ColorSpaceData	ColorSpaceData	NNP
9878	132	188	>	>	XX
9878	132	189	<	<	XX
9878	132	190	ICC	ICC	NNP
9878	132	191	-	-	HYPH
9878	132	192	header	header	NNP
9878	132	193	:	:	:
9878	132	194	ProfileConnectionSpace	profileconnectionspace	XX
9878	132	195	>	>	XX
9878	132	196	XYZ	XYZ	NNP
9878	132	197	<	<	XX
9878	132	198	/ICC	/ICC	NNP
9878	132	199	-	-	HYPH
9878	132	200	header	header	NN
9878	132	201	:	:	:
9878	132	202	ProfileConnectionSpace	profileconnectionspace	XX
9878	132	203	>	>	XX
9878	132	204	<	<	XX
9878	132	205	ICC	ICC	NNP
9878	132	206	-	-	HYPH
9878	132	207	header	header	NN
9878	132	208	:	:	:
9878	132	209	ProfileDateTime>2006:02:02	ProfileDateTime>2006:02:02	NNP
9878	132	210	02:20:00</ICC	02:20:00</icc	CD
9878	132	211	-	-	HYPH
9878	132	212	header	header	NN
9878	132	213	:	:	:
9878	132	214	ProfileDateTime	profiledatetime	UH
9878	132	215	>	>	XX
9878	132	216	<	<	XX
9878	132	217	ICC	ICC	NNP
9878	132	218	-	-	HYPH
9878	132	219	header	header	NNP
9878	132	220	:	:	:
9878	132	221	ProfileFileSignature	profilefilesignature	NN
9878	132	222	>	>	FW
9878	132	223	acsp</ICC	acsp</icc	NN
9878	132	224	-	-	HYPH
9878	132	225	header	header	NN
9878	132	226	:	:	:
9878	132	227	ProfileFileSignature	profilefilesignature	NN
9878	132	228	>	>	XX
9878	132	229	<	<	XX
9878	132	230	ICC	ICC	NNP
9878	132	231	-	-	HYPH
9878	132	232	header	header	NN
9878	132	233	:	:	:
9878	132	234	PrimaryPlatform	PrimaryPlatform	NNP
9878	132	235	>	>	XX
9878	132	236	Apple	Apple	NNP
9878	132	237	Computer	Computer	NNP
9878	132	238	Inc.</ICC	Inc.</ICC	NNP
9878	132	239	-	-	HYPH
9878	132	240	header	header	NN
9878	132	241	:	:	:
9878	132	242	PrimaryPlatform	PrimaryPlatform	NNP
9878	132	243	>	>	XX
9878	132	244	<	<	XX
9878	132	245	ICC	ICC	NNP
9878	132	246	-	-	HYPH
9878	132	247	header	header	NN
9878	132	248	:	:	:
9878	132	249	CMMFlags	cmmflag	NNS
9878	132	250	>	>	XX
9878	132	251	Not	not	RB
9878	132	252	Embedded	embed	VBN
9878	132	253	,	,	,
9878	132	254	Independent</ICC	Independent</ICC	NNP
9878	132	255	-	-	HYPH
9878	132	256	header	header	NNP
9878	132	257	:	:	:
9878	132	258	CMMFlags	cmmflag	NNS
9878	132	259	>	>	XX
9878	132	260	<	<	XX
9878	132	261	ICC	ICC	NNP
9878	132	262	-	-	HYPH
9878	132	263	header	header	NN
9878	132	264	:	:	:
9878	132	265	DeviceManufacturer	DeviceManufacturer	NNP
9878	132	266	>	>	XX
9878	132	267	none</ICC	none</icc	NN
9878	132	268	-	-	HYPH
9878	132	269	header	header	NN
9878	132	270	:	:	:
9878	132	271	DeviceManufacturer	DeviceManufacturer	NNP
9878	132	272	>	>	XX
9878	132	273	<	<	XX
9878	132	274	ICC	ICC	NNP
9878	132	275	-	-	HYPH
9878	132	276	header	header	NNP
9878	132	277	:	:	:
9878	132	278	DeviceModel></ICC	DeviceModel></ICC	NNP
9878	132	279	-	-	NN
9878	132	280	header	header	NNP
9878	132	281	:	:	:
9878	132	282	DeviceModel	DeviceModel	NNP
9878	132	283	>	>	XX
9878	132	284	<	<	XX
9878	132	285	ICC	ICC	NNP
9878	132	286	-	-	HYPH
9878	132	287	header	header	NN
9878	132	288	:	:	:
9878	132	289	DeviceAttributes	DeviceAttributes	NNP
9878	132	290	>	>	XX
9878	132	291	Reflective	reflective	JJ
9878	132	292	,	,	,
9878	132	293	Glossy	Glossy	NNP
9878	132	294	,	,	,
9878	132	295	Positive	positive	JJ
9878	132	296	,	,	,
9878	132	297	Color</ICC-	color</icc-	NN
9878	132	298	header	header	NN
9878	132	299	:	:	:
9878	132	300	DeviceAttributes	DeviceAttributes	NNP
9878	132	301	>	>	XX
9878	132	302	<	<	XX
9878	132	303	ICC	ICC	NNP
9878	132	304	-	-	HYPH
9878	132	305	header	header	NN
9878	132	306	:	:	:
9878	132	307	RenderingIntent	RenderingIntent	NNP
9878	132	308	>	>	NN
9878	132	309	Perceptual</ICC	Perceptual</ICC	NNP
9878	132	310	-	-	HYPH
9878	132	311	header	header	NN
9878	132	312	:	:	:
9878	132	313	RenderingIntent	RenderingIntent	NNP
9878	132	314	>	>	XX
9878	132	315	<	<	XX
9878	132	316	ICC	ICC	NNP
9878	132	317	-	-	HYPH
9878	132	318	header	header	NNP
9878	132	319	:	:	:
9878	132	320	ConnectionSpaceIlluminant>0.9642	ConnectionSpaceIlluminant>0.9642	NNP
9878	132	321	1	1	CD
9878	132	322	0.82491</ICC-	0.82491</icc-	CD
9878	132	323	header	header	NN
9878	132	324	:	:	:
9878	132	325	ConnectionSpaceIlluminant	connectionspaceilluminant	NN
9878	132	326	>	>	XX
9878	132	327	<	<	XX
9878	132	328	ICC	ICC	NNP
9878	132	329	-	-	HYPH
9878	132	330	header	header	NN
9878	132	331	:	:	:
9878	132	332	ProfileCreator	ProfileCreator	NNP
9878	132	333	>	>	XX
9878	132	334	EPSO</ICC	EPSO</ICC	NNP
9878	132	335	-	-	HYPH
9878	132	336	header	header	NN
9878	132	337	:	:	:
9878	132	338	ProfileCreator	ProfileCreator	NNP
9878	132	339	>	>	XX
9878	132	340	<	<	XX
9878	132	341	ICC	ICC	NNP
9878	132	342	-	-	HYPH
9878	132	343	header	header	NNP
9878	132	344	:	:	:
9878	132	345	ProfileID>0</ICC	profileid>0</icc	NN
9878	132	346	-	-	HYPH
9878	132	347	header	header	NNP
9878	132	348	:	:	:
9878	132	349	ProfileID	ProfileID	NNP
9878	132	350	>	>	XX
9878	132	351	<	<	XX
9878	132	352	ICC_Profile	ICC_Profile	NNS
9878	132	353	:	:	:
9878	132	354	ProfileDescription	ProfileDescription	NNP
9878	132	355	>	>	XX
9878	132	356	EPSON	epson	RB
9878	132	357	sRGB</ICC_Profile	sRGB</ICC_Profile	NNS
9878	132	358	:	:	:
9878	132	359	ProfileDescription	ProfileDescription	NNP
9878	132	360	>	>	XX
9878	132	361	<	<	XX
9878	132	362	ICC_Profile	ICC_Profile	NNS
9878	132	363	:	:	:
9878	132	364	RedMatrixColumn>0.43607	redmatrixcolumn>0.43607	CD
9878	132	365	0.22249	0.22249	CD
9878	132	366	0.01392</ICC_Profile	0.01392</icc_profile	CD
9878	132	367	:	:	:
9878	132	368	RedMatrixColumn	redmatrixcolumn	NN
9878	132	369	>	>	XX
9878	132	370	<	<	XX
9878	132	371	ICC_Profile	ICC_Profile	NNS
9878	132	372	:	:	:
9878	132	373	GreenMatrixColumn>0.38515	greenmatrixcolumn>0.38515	CD
9878	132	374	0.71687	0.71687	CD
9878	132	375	0.09708</ICC_Profile	0.09708</icc_profile	CD
9878	132	376	:	:	:
9878	132	377	GreenMatrixColumn	greenmatrixcolumn	ADD
9878	132	378	>	>	XX
9878	132	379	<	<	XX
9878	132	380	ICC_Profile	ICC_Profile	NNS
9878	132	381	:	:	:
9878	132	382	BlueMatrixColumn>0.14307	bluematrixcolumn>0.14307	CD
9878	132	383	0.06061	0.06061	CD
9878	132	384	0.7141</ICC_Profile	0.7141</icc_profile	CD
9878	132	385	:	:	:
9878	132	386	BlueMatrixColumn	bluematrixcolumn	NN
9878	132	387	>	>	XX
9878	132	388	<	<	XX
9878	132	389	ICC_Profile	ICC_Profile	NNS
9878	132	390	:	:	:
9878	132	391	MediaWhitePoint>0.95045	mediawhitepoint>0.95045	CD
9878	132	392	1	1	CD
9878	132	393	1.08905</ICC_Profile	1.08905</icc_profile	CD
9878	132	394	:	:	:
9878	132	395	MediaWhitePoint	mediawhitepoint	ADD
9878	132	396	>	>	XX
9878	132	397	<	<	XX
9878	132	398	ICC_Profile	ICC_Profile	NNS
9878	132	399	:	:	:
9878	132	400	ProfileCopyright	ProfileCopyright	NNP
9878	132	401	>	>	XX
9878	132	402	Copyright	copyright	NN
9878	132	403	(	(	-LRB-
9878	132	404	c	c	NN
9878	132	405	)	)	-RRB-
9878	132	406	SEIKO	seiko	NN
9878	132	407	EPSON	EPSON	NNP
9878	132	408	CORPORATION	corporation	NN
9878	132	409	2000	2000	CD
9878	132	410	-	-	SYM
9878	132	411	2006	2006	CD
9878	132	412	.	.	.
9878	133	1	All	all	DT
9878	133	2	rights	right	NNS
9878	133	3	reserved.</ICC_Profile	reserved.</icc_profile	NN
9878	133	4	:	:	:
9878	133	5	ProfileCopyright	ProfileCopyright	NNP
9878	133	6	>	>	XX
9878	133	7	<	<	XX
9878	133	8	ICC_Profile	ICC_Profile	NNS
9878	133	9	:	:	:
9878	133	10	RedTRC>(Binary	redtrc>(binary	JJ
9878	133	11	data	datum	NNS
9878	133	12	8204	8204	CD
9878	133	13	bytes	byte	NNS
9878	133	14	,	,	,
9878	133	15	use	use	NN
9878	133	16	-b	-b	HYPH
9878	133	17	option	option	NN
9878	133	18	to	to	TO
9878	133	19	extract)</ICC_Profile	extract)</icc_profile	VB
9878	133	20	:	:	:
9878	133	21	RedTRC	redtrc	XX
9878	133	22	>	>	XX
9878	133	23	<	<	XX
9878	133	24	ICC_Profile	ICC_Profile	NNS
9878	133	25	:	:	:
9878	133	26	GreenTRC>(Binary	GreenTRC>(Binary	NNP
9878	133	27	data	data	NN
9878	133	28	8204	8204	CD
9878	133	29	bytes	byte	NNS
9878	133	30	,	,	,
9878	133	31	use	use	NN
9878	133	32	-b	-b	HYPH
9878	133	33	option	option	NN
9878	133	34	to	to	TO
9878	133	35	extract)</ICC_Profile	extract)</icc_profile	VB
9878	133	36	:	:	:
9878	133	37	GreenTRC	GreenTRC	.
9878	133	38	>	>	XX
9878	133	39	<	<	XX
9878	133	40	ICC_Profile	ICC_Profile	NNS
9878	133	41	:	:	:
9878	133	42	BlueTRC>(Binary	BlueTRC>(Binary	NNP
9878	133	43	data	datum	NNS
9878	133	44	8204	8204	CD
9878	133	45	bytes	byte	NNS
9878	133	46	,	,	,
9878	133	47	use	use	NN
9878	133	48	-b	-b	HYPH
9878	133	49	option	option	NN
9878	133	50	to	to	TO
9878	133	51	extract)</ICC_Profile	extract)</icc_profile	VB
9878	133	52	:	:	:
9878	133	53	BlueTRC	BlueTRC	``
9878	133	54	>	>	XX
9878	133	55	<	<	XX
9878	133	56	ICC_Profile	ICC_Profile	NNS
9878	133	57	:	:	:
9878	133	58	MediaBlackPoint>0	MediaBlackPoint>0	NNP
9878	133	59	0	0	CD
9878	133	60	0</ICC_Profile	0</icc_profile	CD
9878	133	61	:	:	:
9878	133	62	MediaBlackPoint	mediablackpoint	ADD
9878	133	63	>	>	XX
9878	133	64	DIGITIZATION	digitization	NN
9878	133	65	OF	of	IN
9878	133	66	TEXT	text	NN
9878	133	67	DOCUMENTS	documents	NN
9878	133	68	USING	USING	NNP
9878	133	69	PDF	PDF	NNP
9878	133	70	/	/	SYM
9878	133	71	A	A	NNP
9878	133	72	|	|	NNP
9878	133	73	HAN	HAN	NNP
9878	133	74	AND	and	CC
9878	133	75	WAN	WAN	NNP
9878	133	76	63	63	CD
9878	133	77	HTTPS://DOI.ORG/10.6017	HTTPS://DOI.ORG/10.6017	NNS
9878	133	78	/	/	SYM
9878	133	79	ITAL.V37I1.9878	ital.v37i1.9878	JJ
9878	133	80	APPENDIX	APPENDIX	NNP
9878	133	81	B	b	NN
9878	133	82	:	:	:
9878	133	83	SAMPLE	SAMPLE	NNP
9878	133	84	CODE	code	NN
9878	133	85	TO	to	IN
9878	133	86	CONVERT	CONVERT	NNP
9878	133	87	PDF	PDF	NNP
9878	133	88	/	/	SYM
9878	133	89	A-2	A-2	NNP
9878	133	90	BACK	BACK	VBZ
9878	133	91	TO	to	IN
9878	133	92	JPEG2000S	jpeg2000s	NN
9878	133	93	/	/	SYM
9878	133	94	*	*	NFP
9878	133	95	Assumption	assumption	NN
9878	133	96	:	:	:
9878	133	97	The	the	DT
9878	133	98	PDF	PDF	NNP
9878	133	99	/	/	SYM
9878	133	100	A-2b	A-2b	NNP
9878	133	101	file	file	NN
9878	133	102	was	be	VBD
9878	133	103	specifically	specifically	RB
9878	133	104	generated	generate	VBN
9878	133	105	from	from	IN
9878	133	106	image	image	NN
9878	133	107	objects	object	NNS
9878	133	108	converted	convert	VBN
9878	133	109	from	from	IN
9878	133	110	TIFF	TIFF	NNP
9878	133	111	images	image	NNS
9878	133	112	with	with	IN
9878	133	113	JPXDecode	JPXDecode	NNP
9878	133	114	along	along	IN
9878	133	115	with	with	IN
9878	133	116	page	page	NN
9878	133	117	-	-	HYPH
9878	133	118	level	level	NN
9878	133	119	metadata	metadata	NN
9878	133	120	*	*	NFP
9878	133	121	/	/	SYM
9878	133	122	public	public	JJ
9878	133	123	static	static	JJ
9878	133	124	void	void	NN
9878	133	125	parse(String	parse(stre	VBG
9878	133	126	src	src	NNP
9878	133	127	,	,	,
9878	133	128	String	string	NN
9878	133	129	dest	d	JJS
9878	133	130	)	)	-RRB-
9878	133	131	throws	throw	VBZ
9878	133	132	IOException	ioexception	NN
9878	133	133	{	{	-LRB-
9878	133	134	PdfReader	PdfReader	NNP
9878	133	135	reader	reader	NN
9878	133	136	=	=	SYM
9878	133	137	new	new	NNP
9878	133	138	PdfReader(src	PdfReader(src	NNP
9878	133	139	)	)	-RRB-
9878	133	140	;	;	:
9878	133	141	PdfObject	pdfobject	VB
9878	133	142	obj	obj	NN
9878	133	143	;	;	:
9878	133	144	int	int	VB
9878	133	145	counter	counter	NN
9878	133	146	=	=	NFP
9878	133	147	0	0	CD
9878	133	148	;	;	:
9878	133	149	for(int	for(int	NN
9878	133	150	i	i	PRP
9878	133	151	=	=	CC
9878	133	152	1	1	CD
9878	133	153	;	;	:
9878	133	154	i	i	PRP
9878	133	155	<	<	XX
9878	133	156	=	=	NFP
9878	133	157	reader.getXrefSize	reader.getxrefsize	XX
9878	133	158	(	(	-LRB-
9878	133	159	)	)	-RRB-
9878	133	160	;	;	:
9878	133	161	i	i	PRP
9878	133	162	+	+	SYM
9878	133	163	+	+	SYM
9878	133	164	)	)	-RRB-
9878	133	165	{	{	-LRB-
9878	133	166	obj	obj	UH
9878	133	167	=	=	NFP
9878	133	168	reader.getPdfObject(i	reader.getPdfObject(i	NNP
9878	133	169	)	)	-RRB-
9878	133	170	;	;	:
9878	133	171	if(obj	if(obj	NN
9878	133	172	!	!	.
9878	133	173	=	=	NFP
9878	133	174	null	null	NNP
9878	133	175	&	&	CC
9878	133	176	&	&	CC
9878	133	177	obj.isStream	obj.isstream	ADD
9878	133	178	(	(	-LRB-
9878	133	179	)	)	-RRB-
9878	133	180	)	)	-RRB-
9878	133	181	{	{	-LRB-
9878	133	182	PRStream	prstream	NN
9878	133	183	stream	stream	NN
9878	133	184	=	=	NFP
9878	133	185	(	(	-LRB-
9878	133	186	PRStream	prstream	NN
9878	133	187	)	)	-RRB-
9878	133	188	obj	obj	UH
9878	133	189	;	;	:
9878	133	190	byte	byte	NN
9878	133	191	[	[	-LRB-
9878	133	192	]	]	-RRB-
9878	133	193	b	b	NN
9878	133	194	;	;	:
9878	133	195	try	try	VB
9878	133	196	{	{	-LRB-
9878	133	197	b	b	NN
9878	133	198	=	=	SYM
9878	133	199	PdfReader.getStreamBytes(stream	PdfReader.getStreamBytes(stream	NNP
9878	133	200	)	)	-RRB-
9878	133	201	;	;	:
9878	133	202	}	}	-RRB-
9878	133	203	catch(UnsupportedPdfException	catch(UnsupportedPdfException	NNP
9878	133	204	e	e	NNP
9878	133	205	)	)	-RRB-
9878	133	206	{	{	-LRB-
9878	133	207	b	b	NN
9878	133	208	=	=	SYM
9878	133	209	PdfReader.getStreamBytesRaw(stream	PdfReader.getStreamBytesRaw(stream	NNP
9878	133	210	)	)	-RRB-
9878	133	211	;	;	:
9878	133	212	}	}	-RRB-
9878	133	213	PdfObject	PdfObject	NNP
9878	133	214	pdfsubtype	pdfsubtype	NN
9878	133	215	=	=	SYM
9878	133	216	stream.get(PdfName	stream.get(pdfname	NN
9878	133	217	.	.	.
9878	133	218	SUBTYPE	SUBTYPE	NNP
9878	133	219	)	)	-RRB-
9878	133	220	;	;	:
9878	133	221	FileOutputStream	fileoutputstream	ADD
9878	133	222	fos	fos	NN
9878	133	223	=	=	SYM
9878	133	224	null	null	NN
9878	133	225	;	;	:
9878	133	226	if	if	IN
9878	133	227	(	(	-LRB-
9878	133	228	pdfsubtype	pdfsubtype	NNP
9878	133	229	!	!	.
9878	133	230	=	=	NFP
9878	133	231	null	null	NNP
9878	133	232	&	&	CC
9878	133	233	&	&	CC
9878	133	234	pdfsubtype.toString().equals(PdfName	pdfsubtype.toString().equals(PdfName	NNP
9878	133	235	.	.	.
9878	133	236	XML.toString	XML.toString	NNP
9878	133	237	(	(	-LRB-
9878	133	238	)	)	-RRB-
9878	133	239	)	)	-RRB-
9878	133	240	)	)	-RRB-
9878	133	241	{	{	-LRB-
9878	133	242	fos	fos	NN
9878	133	243	=	=	SYM
9878	133	244	new	new	JJ
9878	133	245	FileOutputStream(String.format(dest	FileOutputStream(String.format(dest	NNP
9878	133	246	+	+	CC
9878	133	247	"	"	``
9878	133	248	_	_	NNP
9878	133	249	xml/	xml/	NNP
9878	133	250	"	"	''
9878	133	251	+	+	CC
9878	133	252	counter+".xml	counter+".xml	NN
9878	133	253	"	"	''
9878	133	254	,	,	,
9878	133	255	i	i	PRP
9878	133	256	)	)	-RRB-
9878	133	257	)	)	-RRB-
9878	133	258	;	;	:
9878	133	259	System.out.println("Page	system.out.println("page	NN
9878	133	260	Metadata	Metadata	NNP
9878	133	261	Extracted	extract	VBN
9878	133	262	!	!	.
9878	134	1	")	")	``
9878	134	2	;	;	:
9878	134	3	}	}	-RRB-
9878	134	4	if	if	IN
9878	134	5	(	(	-LRB-
9878	134	6	pdfsubtype	pdfsubtype	NNP
9878	134	7	!	!	.
9878	134	8	=	=	NFP
9878	134	9	null	null	NNP
9878	134	10	&	&	CC
9878	134	11	&	&	CC
9878	134	12	pdfsubtype.toString().equals(PdfName	pdfsubtype.toString().equals(PdfName	NNP
9878	134	13	.	.	.
9878	134	14	IMAGE.toString	IMAGE.toString	''
9878	134	15	(	(	-LRB-
9878	134	16	)	)	-RRB-
9878	134	17	)	)	-RRB-
9878	134	18	)	)	-RRB-
9878	134	19	{	{	-LRB-
9878	134	20	counter	counter	NN
9878	134	21	+	+	NNP
9878	134	22	+	+	SYM
9878	134	23	;	;	:
9878	134	24	fos	fos	NNP
9878	134	25	=	=	SYM
9878	134	26	new	new	JJ
9878	134	27	FileOutputStream(String.format(dest	FileOutputStream(String.format(dest	NNP
9878	134	28	+	+	CC
9878	134	29	"	"	``
9878	134	30	_	_	NNP
9878	134	31	jp2/	jp2/	NNP
9878	134	32	"	"	''
9878	134	33	+	+	NNP
9878	134	34	counter+".jp2	counter+".jp2	NNP
9878	134	35	"	"	''
9878	134	36	,	,	,
9878	134	37	i	i	PRP
9878	134	38	)	)	-RRB-
9878	134	39	)	)	-RRB-
9878	134	40	;	;	:
9878	134	41	}	}	-RRB-
9878	134	42	if	if	IN
9878	134	43	(	(	-LRB-
9878	134	44	fos	fos	JJ
9878	134	45	!	!	.
9878	134	46	=	=	SYM
9878	134	47	null	null	NN
9878	134	48	)	)	-RRB-
9878	134	49	{	{	-LRB-
9878	134	50	fos.write(b	fos.write(b	NNP
9878	134	51	)	)	-RRB-
9878	134	52	;	;	:
9878	134	53	fos.flush	fos.flush	NNP
9878	134	54	(	(	-LRB-
9878	134	55	)	)	-RRB-
9878	134	56	;	;	.
9878	134	57	fos.close	fos.close	NNP
9878	134	58	(	(	-LRB-
9878	134	59	)	)	-RRB-
9878	134	60	;	;	:
9878	134	61	System.out.println("JPEG2000s	System.out.println("JPEG2000s	NNP
9878	134	62	Conversion	Conversion	NNP
9878	134	63	from	from	IN
9878	134	64	PDF	PDF	NNP
9878	134	65	completed	complete	VBN
9878	134	66	!	!	.
9878	135	1	")	")	``
9878	135	2	;	;	:
9878	135	3	}	}	-RRB-
9878	135	4	}	}	-RRB-
9878	135	5	}	}	-RRB-
9878	135	6	/	/	NFP
9878	135	7	*	*	NFP
9878	135	8	Then	then	RB
9878	135	9	Use	Use	NNP
9878	135	10	ImageMagick	ImageMagick	NNP
9878	135	11	library	library	NN
9878	135	12	to	to	TO
9878	135	13	convert	convert	VB
9878	135	14	JPEG2000s	JPEG2000s	NNP
9878	135	15	to	to	IN
9878	135	16	TIFFs	TIFFs	NNP
9878	135	17	*	*	NFP
9878	135	18	/	/	SYM
9878	135	19	INFORMATION	INFORMATION	NNP
9878	135	20	TECHNOLOGY	TECHNOLOGY	NNP
9878	135	21	AND	and	CC
9878	135	22	LIBRARIES	library	NNS
9878	135	23	|	|	NNP
9878	135	24	MARCH	MARCH	NNS
9878	135	25	2018	2018	CD
9878	135	26	64	64	CD
9878	135	27	REFERENCES	reference	NNS
9878	135	28	1	1	CD
9878	135	29	PDF-Tools.com	PDF-Tools.com	NNP
9878	135	30	and	and	CC
9878	135	31	PDF	PDF	NNP
9878	135	32	Association	Association	NNP
9878	135	33	,	,	,
9878	135	34	“	"	``
9878	135	35	PDF	PDF	NNP
9878	135	36	/	/	SYM
9878	135	37	A	a	NN
9878	135	38	—	—	:
9878	135	39	The	the	DT
9878	135	40	Standard	Standard	NNP
9878	135	41	for	for	IN
9878	135	42	Long	Long	NNP
9878	135	43	-	-	HYPH
9878	135	44	Term	term	NN
9878	135	45	Archiving	archiving	NN
9878	135	46	,	,	,
9878	135	47	”	"	''
9878	135	48	version	version	NN
9878	135	49	2.4	2.4	CD
9878	135	50	,	,	,
9878	135	51	white	white	JJ
9878	135	52	paper	paper	NN
9878	135	53	,	,	,
9878	135	54	May	May	NNP
9878	135	55	20	20	CD
9878	135	56	,	,	,
9878	135	57	2009	2009	CD
9878	135	58	,	,	,
9878	135	59	http://www.pdf-	http://www.pdf-	NNP
9878	135	60	tools.com/public/downloads/whitepapers/whitepaper-pdfa.pdf	tools.com/public/downloads/whitepapers/whitepaper-pdfa.pdf	ADD
9878	135	61	;	;	:
9878	135	62	Duff	Duff	NNP
9878	135	63	Johnson	Johnson	NNP
9878	135	64	,	,	,
9878	135	65	“	"	``
9878	135	66	White	White	NNP
9878	135	67	Paper	Paper	NNP
9878	135	68	:	:	:
9878	135	69	How	how	WRB
9878	135	70	to	to	TO
9878	135	71	Implement	implement	VB
9878	135	72	PDF	PDF	NNP
9878	135	73	/	/	,
9878	135	74	A	a	NN
9878	135	75	,	,	,
9878	135	76	”	"	''
9878	135	77	Talking	talk	VBG
9878	135	78	PDF	PDF	NNP
9878	135	79	,	,	,
9878	135	80	August	August	NNP
9878	135	81	24	24	CD
9878	135	82	,	,	,
9878	135	83	2010	2010	CD
9878	135	84	,	,	,
9878	135	85	https://talkingpdf.org/white-paper-	https://talkingpdf.org/white-paper-	VBZ
9878	135	86	how	how	RB
9878	135	87	-	-	HYPH
9878	135	88	to	to	IN
9878	135	89	-	-	HYPH
9878	135	90	implement	implement	NN
9878	135	91	-	-	HYPH
9878	135	92	pdfa/	pdfa/	NNS
9878	135	93	;	;	:
9878	135	94	Alexandra	Alexandra	NNP
9878	135	95	Oettler	Oettler	NNP
9878	135	96	,	,	,
9878	135	97	“	"	``
9878	135	98	PDF	PDF	NNP
9878	135	99	/	/	SYM
9878	135	100	A	a	NN
9878	135	101	in	in	IN
9878	135	102	a	a	DT
9878	135	103	Nutshell	Nutshell	NNP
9878	135	104	2.0	2.0	CD
9878	135	105	:	:	:
9878	135	106	PDF	pdf	NN
9878	135	107	for	for	IN
9878	135	108	Long	Long	NNP
9878	135	109	-	-	HYPH
9878	135	110	Term	Term	NNP
9878	135	111	Archiving	Archiving	NNP
9878	135	112	,	,	,
9878	135	113	”	"	''
9878	135	114	Association	Association	NNP
9878	135	115	for	for	IN
9878	135	116	Digital	Digital	NNP
9878	135	117	Standards	Standards	NNP
9878	135	118	,	,	,
9878	135	119	2013	2013	CD
9878	135	120	,	,	,
9878	135	121	https://www.pdfa.org/wp-	https://www.pdfa.org/wp-	NNP
9878	135	122	content	content	NN
9878	135	123	/	/	SYM
9878	135	124	until2016_uploads/2013/05	until2016_uploads/2013/05	NNP
9878	135	125	/	/	SYM
9878	135	126	PDFA_in_a_Nutshell_211.pdf	pdfa_in_a_nutshell_211.pdf	NN
9878	135	127	;	;	:
9878	135	128	Library	Library	NNP
9878	135	129	of	of	IN
9878	135	130	Congress	Congress	NNP
9878	135	131	,	,	,
9878	135	132	“	"	``
9878	135	133	PDF	PDF	NNP
9878	135	134	/	/	,
9878	135	135	A	A	NNP
9878	135	136	,	,	,
9878	135	137	PDF	PDF	NNP
9878	135	138	for	for	IN
9878	135	139	Long	Long	NNP
9878	135	140	-	-	HYPH
9878	135	141	Term	Term	NNP
9878	135	142	Preservation	Preservation	NNP
9878	135	143	,	,	,
9878	135	144	”	"	''
9878	135	145	last	last	JJ
9878	135	146	modified	modify	VBN
9878	135	147	July	July	NNP
9878	135	148	27	27	CD
9878	135	149	,	,	,
9878	135	150	2017	2017	CD
9878	135	151	,	,	,
9878	135	152	https://www.loc.gov/preservation/digital/formats/fdd/fdd000318.shtml	https://www.loc.gov/preservation/digital/formats/fdd/fdd000318.shtml	NN
9878	135	153	.	.	.
9878	136	1	2	2	LS
9878	136	2	Library	Library	NNP
9878	136	3	of	of	IN
9878	136	4	Congress	Congress	NNP
9878	136	5	,	,	,
9878	136	6	“	"	``
9878	136	7	The	the	DT
9878	136	8	Time	Time	NNP
9878	136	9	and	and	CC
9878	136	10	Place	Place	NNP
9878	136	11	for	for	IN
9878	136	12	PDF	PDF	NNP
9878	136	13	:	:	:
9878	136	14	An	an	DT
9878	136	15	Interview	interview	NN
9878	136	16	with	with	IN
9878	136	17	Duff	Duff	NNP
9878	136	18	Johnson	Johnson	NNP
9878	136	19	of	of	IN
9878	136	20	the	the	DT
9878	136	21	PDF	PDF	NNP
9878	136	22	Association	Association	NNP
9878	136	23	,	,	,
9878	136	24	”	"	''
9878	136	25	The	the	DT
9878	136	26	Signal	Signal	NNP
9878	136	27	(	(	-LRB-
9878	136	28	blog	blog	NN
9878	136	29	)	)	-RRB-
9878	136	30	,	,	,
9878	136	31	December	December	NNP
9878	136	32	12	12	CD
9878	136	33	,	,	,
9878	136	34	2017	2017	CD
9878	136	35	,	,	,
9878	136	36	https://blogs.loc.gov/thesignal/2017/12/the-time-and-place-for-pdf-an-interview-with-duff-	https://blogs.loc.gov/thesignal/2017/12/the-time-and-place-for-pdf-an-interview-with-duff-	NNP
9878	136	37	johnson	johnson	NNP
9878	136	38	-	-	HYPH
9878	136	39	of	of	IN
9878	136	40	-	-	HYPH
9878	136	41	the	the	DT
9878	136	42	-	-	HYPH
9878	136	43	pdf	pdf	NN
9878	136	44	-	-	NN
9878	136	45	association/.	association/.	JJ
9878	137	1	3	3	CD
9878	137	2	Yan	Yan	NNP
9878	137	3	Han	Han	NNP
9878	137	4	,	,	,
9878	137	5	“	"	``
9878	137	6	Beyond	beyond	IN
9878	137	7	TIFF	TIFF	NNP
9878	137	8	and	and	CC
9878	137	9	JPEG2000	JPEG2000	NNP
9878	137	10	:	:	:
9878	137	11	PDF	PDF	NNP
9878	137	12	/	/	SYM
9878	137	13	A	A	NNP
9878	137	14	as	as	IN
9878	137	15	an	an	DT
9878	137	16	OAIS	OAIS	NNP
9878	137	17	Submission	Submission	NNP
9878	137	18	Information	Information	NNP
9878	137	19	Package	Package	NNP
9878	137	20	Container	Container	NNP
9878	137	21	,	,	,
9878	137	22	”	"	''
9878	137	23	Library	library	JJ
9878	137	24	Hi	Hi	NNP
9878	137	25	Tech	Tech	NNP
9878	137	26	33	33	CD
9878	137	27	,	,	,
9878	137	28	no	no	UH
9878	137	29	.	.	.
9878	138	1	3	3	CD
9878	138	2	(	(	-LRB-
9878	138	3	2015	2015	CD
9878	138	4	)	)	-RRB-
9878	138	5	:	:	:
9878	138	6	409–23	409–23	CD
9878	138	7	,	,	,
9878	138	8	https://doi.org/10.1108/LHT-06-2015-	https://doi.org/10.1108/LHT-06-2015-	NNP
9878	138	9	0068	0068	CD
9878	138	10	.	.	.
9878	139	1	4	4	CD
9878	139	2	Federal	Federal	NNP
9878	139	3	Agencies	Agencies	NNPS
9878	139	4	Digital	Digital	NNP
9878	139	5	Guidelines	Guidelines	NNP
9878	139	6	Initiative	Initiative	NNP
9878	139	7	,	,	,
9878	139	8	Technical	Technical	NNP
9878	139	9	Guidelines	Guidelines	NNP
9878	139	10	for	for	IN
9878	139	11	Digitizing	Digitizing	NNP
9878	139	12	Cultural	Cultural	NNP
9878	139	13	Heritage	Heritage	NNP
9878	139	14	Materials	Materials	NNPS
9878	139	15	.	.	.
9878	140	1	(	(	-LRB-
9878	140	2	Washington	Washington	NNP
9878	140	3	,	,	,
9878	140	4	DC	DC	NNP
9878	140	5	:	:	:
9878	140	6	Federal	Federal	NNP
9878	140	7	Agencies	Agencies	NNPS
9878	140	8	Digital	Digital	NNP
9878	140	9	Guidelines	Guidelines	NNP
9878	140	10	Initiative	Initiative	NNP
9878	140	11	,	,	,
9878	140	12	2016	2016	CD
9878	140	13	)	)	-RRB-
9878	140	14	,	,	,
9878	140	15	http://www.digitizationguidelines.gov/guidelines/FADGI%20Federal%20%20Agencies%20D	http://www.digitizationguidelines.gov/guidelines/fadgi%20federal%20%20agencies%20d	ADD
9878	140	16	igital%20Guidelines%20Initiative-2016%20Final_rev1.pdf	igital%20Guidelines%20Initiative-2016%20Final_rev1.pdf	NNS
9878	140	17	.	.	.
9878	141	1	5	5	CD
9878	141	2	Duff	Duff	NNP
9878	141	3	Johnson	Johnson	NNP
9878	141	4	,	,	,
9878	141	5	“	"	``
9878	141	6	US	US	NNP
9878	141	7	Federal	Federal	NNP
9878	141	8	Agencies	Agencies	NNPS
9878	141	9	Approve	Approve	NNP
9878	141	10	PDF	PDF	NNP
9878	141	11	/	/	,
9878	141	12	A	a	NN
9878	141	13	,	,	,
9878	141	14	”	"	''
9878	141	15	PDF	PDF	NNP
9878	141	16	Association	Association	NNP
9878	141	17	,	,	,
9878	141	18	September	September	NNP
9878	141	19	2	2	CD
9878	141	20	,	,	,
9878	141	21	2016	2016	CD
9878	141	22	,	,	,
9878	141	23	http://www.pdfa.org/new/us-federal-agencies-approve-pdfa/.	http://www.pdfa.org/new/us-federal-agencies-approve-pdfa/.	CD
9878	142	1	6	6	CD
9878	142	2	Bruno	Bruno	NNP
9878	142	3	Lowagie	Lowagie	NNP
9878	142	4	,	,	,
9878	142	5	iText	iText	NNP
9878	142	6	in	in	IN
9878	142	7	Action	Action	NNP
9878	142	8	,	,	,
9878	142	9	2nd	2nd	JJ
9878	142	10	ed	ed	NN
9878	142	11	.	.	.
9878	143	1	(	(	-LRB-
9878	143	2	Stamford	Stamford	NNP
9878	143	3	,	,	,
9878	143	4	CT	CT	NNP
9878	143	5	:	:	:
9878	143	6	Manning	manning	NN
9878	143	7	,	,	,
9878	143	8	2010	2010	CD
9878	143	9	)	)	-RRB-
9878	143	10	.	.	.
9878	144	1	7	7	LS
9878	144	2	“	"	``
9878	144	3	iText	iText	NNP
9878	144	4	5.4.4	5.4.4	CD
9878	144	5	,	,	,
9878	144	6	”	"	''
9878	144	7	iText	itext	RB
9878	144	8	,	,	,
9878	144	9	last	last	JJ
9878	144	10	modified	modify	VBN
9878	144	11	September	September	NNP
9878	144	12	16	16	CD
9878	144	13	,	,	,
9878	144	14	2013	2013	CD
9878	144	15	,	,	,
9878	144	16	http://itextpdf.com/changelog/544	http://itextpdf.com/changelog/544	NNP
9878	144	17	.	.	.
9878	145	1	8	8	CD
9878	145	2	Timothy	Timothy	NNP
9878	145	3	Robert	Robert	NNP
9878	145	4	Hart	Hart	NNP
9878	145	5	and	and	CC
9878	145	6	Denise	Denise	NNP
9878	145	7	de	de	NNP
9878	145	8	Vries	Vries	NNP
9878	145	9	,	,	,
9878	145	10	“	"	``
9878	145	11	Metadata	Metadata	NNP
9878	145	12	Provenance	Provenance	NNP
9878	145	13	and	and	CC
9878	145	14	Vulnerability	vulnerability	NN
9878	145	15	,	,	,
9878	145	16	”	"	''
9878	145	17	Information	Information	NNP
9878	145	18	Technology	Technology	NNP
9878	145	19	and	and	CC
9878	145	20	Libraries	Libraries	NNP
9878	145	21	36	36	CD
9878	145	22	,	,	,
9878	145	23	no	no	UH
9878	145	24	.	.	.
9878	146	1	4	4	CD
9878	146	2	(	(	-LRB-
9878	146	3	2017	2017	CD
9878	146	4	)	)	-RRB-
9878	146	5	,	,	,
9878	146	6	https://doi.org/10.6017/ital.v36i4.10146	https://doi.org/10.6017/ital.v36i4.10146	NNP
9878	146	7	.	.	.
9878	147	1	9	9	CD
9878	147	2	Johan	Johan	NNP
9878	147	3	Van	Van	NNP
9878	147	4	der	der	IN
9878	147	5	Knijff	Knijff	NNP
9878	147	6	,	,	,
9878	147	7	“	"	``
9878	147	8	JPEG	JPEG	NNP
9878	147	9	2000	2000	CD
9878	147	10	for	for	IN
9878	147	11	Long	Long	NNP
9878	147	12	-	-	HYPH
9878	147	13	Term	Term	NNP
9878	147	14	Preservation	preservation	NN
9878	147	15	:	:	:
9878	147	16	JP2	JP2	NNP
9878	147	17	as	as	IN
9878	147	18	a	a	DT
9878	147	19	Preservation	Preservation	NNP
9878	147	20	Format	Format	NNP
9878	147	21	,	,	,
9878	147	22	”	"	''
9878	147	23	D-	D-	NNP
9878	147	24	Lib	Lib	NNP
9878	147	25	17	17	CD
9878	147	26	,	,	,
9878	147	27	no	no	UH
9878	147	28	.	.	.
9878	148	1	5/6	5/6	CD
9878	148	2	(	(	-LRB-
9878	148	3	2011	2011	CD
9878	148	4	)	)	-RRB-
9878	148	5	,	,	,
9878	148	6	https://doi.org/10.1045/may2011-vanderknijff	https://doi.org/10.1045/may2011-vanderknijff	ADD
9878	148	7	.	.	.
9878	149	1	10	10	CD
9878	149	2	PDF	PDF	NNP
9878	149	3	Association	Association	NNP
9878	149	4	,	,	,
9878	149	5	“	"	``
9878	149	6	How	how	WRB
9878	149	7	veraPDF	veraPDF	NNP
9878	149	8	does	do	VBZ
9878	149	9	PDF	PDF	NNP
9878	149	10	/	/	,
9878	149	11	A	A	NNP
9878	149	12	Validation	validation	NN
9878	149	13	,	,	,
9878	149	14	”	"	''
9878	149	15	2016	2016	CD
9878	149	16	,	,	,
9878	149	17	http://www.pdfa.org/how-	http://www.pdfa.org/how-	NNP
9878	149	18	verapdf	verapdf	NN
9878	149	19	-	-	HYPH
9878	149	20	does	do	VBZ
9878	149	21	-	-	HYPH
9878	149	22	pdfa	pdfa	NN
9878	149	23	-	-	HYPH
9878	149	24	validation/.	validation/.	NN
9878	150	1	http://www.pdf-tools.com/public/downloads/whitepapers/whitepaper-pdfa.pdf	http://www.pdf-tools.com/public/downloads/whitepapers/whitepaper-pdfa.pdf	NNP
9878	150	2	http://www.pdf-tools.com/public/downloads/whitepapers/whitepaper-pdfa.pdf	http://www.pdf-tools.com/public/downloads/whitepapers/whitepaper-pdfa.pdf	NNP
9878	150	3	https://talkingpdf.org/white-paper-how-to-implement-pdfa/	https://talkingpdf.org/white-paper-how-to-implement-pdfa/	NNP
9878	150	4	https://talkingpdf.org/white-paper-how-to-implement-pdfa/	https://talkingpdf.org/white-paper-how-to-implement-pdfa/	NNP
9878	150	5	https://www.pdfa.org/wp-content/until2016_uploads/2013/05/PDFA_in_a_Nutshell_211.pdf	https://www.pdfa.org/wp-content/until2016_uploads/2013/05/PDFA_in_a_Nutshell_211.pdf	NNP
9878	150	6	https://www.pdfa.org/wp-content/until2016_uploads/2013/05/PDFA_in_a_Nutshell_211.pdf	https://www.pdfa.org/wp-content/until2016_uploads/2013/05/pdfa_in_a_nutshell_211.pdf	NN
9878	150	7	https://www.loc.gov/preservation/digital/formats/fdd/fdd000318.shtml	https://www.loc.gov/preservation/digital/formats/fdd/fdd000318.shtml	NNP
9878	150	8	https://blogs.loc.gov/thesignal/2017/12/the-time-and-place-for-pdf-an-interview-with-duff-johnson-of-the-pdf-association/	https://blogs.loc.gov/thesignal/2017/12/the-time-and-place-for-pdf-an-interview-with-duff-johnson-of-the-pdf-association/	NNP
9878	150	9	https://blogs.loc.gov/thesignal/2017/12/the-time-and-place-for-pdf-an-interview-with-duff-johnson-of-the-pdf-association/	https://blogs.loc.gov/thesignal/2017/12/the-time-and-place-for-pdf-an-interview-with-duff-johnson-of-the-pdf-association/	NNP
9878	150	10	https://blogs.loc.gov/thesignal/2017/12/the-time-and-place-for-pdf-an-interview-with-duff-johnson-of-the-pdf-association/	https://blogs.loc.gov/thesignal/2017/12/the-time-and-place-for-pdf-an-interview-with-duff-johnson-of-the-pdf-association/	NNPS
9878	150	11	https://blogs.loc.gov/thesignal/2017/12/the-time-and-place-for-pdf-an-interview-with-duff-johnson-of-the-pdf-association/	https://blogs.loc.gov/thesignal/2017/12/the-time-and-place-for-pdf-an-interview-with-duff-johnson-of-the-pdf-association/	NNP
9878	150	12	https://doi.org/10.1108/LHT-06-2015-0068	https://doi.org/10.1108/LHT-06-2015-0068	NNP
9878	150	13	https://doi.org/10.1108/LHT-06-2015-0068	https://doi.org/10.1108/LHT-06-2015-0068	NNS
9878	150	14	http://www.digitizationguidelines.gov/guidelines/FADGI%20Federal%20%20Agencies%20Digital%20Guidelines%20Initiative-2016%20Final_rev1.pdf	http://www.digitizationguidelines.gov/guidelines/FADGI%20Federal%20%20Agencies%20Digital%20Guidelines%20Initiative-2016%20Final_rev1.pdf	NNP
9878	150	15	http://www.digitizationguidelines.gov/guidelines/FADGI%20Federal%20%20Agencies%20Digital%20Guidelines%20Initiative-2016%20Final_rev1.pdf	http://www.digitizationguidelines.gov/guidelines/FADGI%20Federal%20%20Agencies%20Digital%20Guidelines%20Initiative-2016%20Final_rev1.pdf	NNP
9878	150	16	http://www.digitizationguidelines.gov/guidelines/FADGI%20Federal%20%20Agencies%20Digital%20Guidelines%20Initiative-2016%20Final_rev1.pdf	http://www.digitizationguidelines.gov/guidelines/FADGI%20Federal%20%20Agencies%20Digital%20Guidelines%20Initiative-2016%20Final_rev1.pdf	NNP
9878	150	17	http://www.digitizationguidelines.gov/guidelines/FADGI%20Federal%20%20Agencies%20Digital%20Guidelines%20Initiative-2016%20Final_rev1.pdf	http://www.digitizationguidelines.gov/guidelines/FADGI%20Federal%20%20Agencies%20Digital%20Guidelines%20Initiative-2016%20Final_rev1.pdf	NNP
9878	150	18	https://www.pdfa.org/new/us-federal-agencies-approve-pdfa/	https://www.pdfa.org/new/us-federal-agencies-approve-pdfa/	NNP
9878	150	19	https://www.pdfa.org/new/us-federal-agencies-approve-pdfa/	https://www.pdfa.org/new/us-federal-agencies-approve-pdfa/	NNP
9878	150	20	https://www.pdfa.org/new/us-federal-agencies-approve-pdfa/	https://www.pdfa.org/new/us-federal-agencies-approve-pdfa/	NNP
9878	150	21	http://itextpdf.com/changelog/544	http://itextpdf.com/changelog/544	NNP
9878	150	22	http://itextpdf.com/changelog/544	http://itextpdf.com/changelog/544	NNP
9878	150	23	https://doi.org/10.6017/ital.v36i4.10146	https://doi.org/10.6017/ital.v36i4.10146	NNP
9878	150	24	https://doi.org/10.6017/ital.v36i4.10146	https://doi.org/10.6017/ital.v36i4.10146	NNP
9878	150	25	https://doi.org/10.1045/may2011-vanderknijff	https://doi.org/10.1045/may2011-vanderknijff	NNP
9878	150	26	https://www.pdfa.org/how-verapdf-does-pdfa-validation/	https://www.pdfa.org/how-verapdf-does-pdfa-validation/	NNP
9878	150	27	https://www.pdfa.org/how-verapdf-does-pdfa-validation/	https://www.pdfa.org/how-verapdf-does-pdfa-validation/	UH
9878	150	28	https://www.pdfa.org/how-verapdf-does-pdfa-validation/	https://www.pdfa.org/how-verapdf-does-pdfa-validation/	NNP
9878	150	29	Abstract	Abstract	NNP
9878	150	30	Background	Background	NNP
9878	150	31	Goals	Goals	NNPS
9878	150	32	and	and	CC
9878	150	33	Tasks	Tasks	NNPS
9878	150	34	Choices	Choices	NNPS
9878	150	35	of	of	IN
9878	150	36	PDF	PDF	NNP
9878	150	37	/	/	SYM
9878	150	38	A	A	NNP
9878	150	39	Standards	Standards	NNPS
9878	150	40	and	and	CC
9878	150	41	Conformance	Conformance	NNP
9878	150	42	Level	Level	NNP
9878	150	43	Data	Data	NNP
9878	150	44	Source	Source	NNP
9878	150	45	PDF	PDF	NNP
9878	150	46	/	/	SYM
9878	150	47	A	a	NN
9878	150	48	and	and	CC
9878	150	49	Image	Image	NNP
9878	150	50	Manipulation	Manipulation	NNP
9878	150	51	Tools	Tools	NNPS
9878	150	52	Metadata	Metadata	NNP
9878	150	53	Extraction	extraction	NN
9878	150	54	Tools	tool	NNS
9878	150	55	and	and	CC
9878	150	56	Color	Color	NNP
9878	150	57	Profiles	Profiles	NNPS
9878	150	58	Implementation	Implementation	NNP
9878	150	59	Converting	convert	VBG
9878	150	60	and	and	CC
9878	150	61	Ordering	ordering	NN
9878	150	62	TIFFs	TIFFs	NNPS
9878	150	63	into	into	IN
9878	150	64	a	a	DT
9878	150	65	Single	single	JJ
9878	150	66	PDF	PDF	NNP
9878	150	67	/	/	SYM
9878	150	68	A-2	A-2	NNP
9878	150	69	File	File	NNP
9878	150	70	Converting	Converting	NNP
9878	150	71	PDF	PDF	NNP
9878	150	72	/	/	SYM
9878	150	73	A-2	A-2	NNP
9878	150	74	Files	file	VBZ
9878	150	75	back	back	RB
9878	150	76	to	to	IN
9878	150	77	TIFFs	TIFFs	NNPS
9878	150	78	and	and	CC
9878	150	79	JPEG2000s	JPEG2000s	NNP
9878	150	80	PDF	PDF	NNP
9878	150	81	/	/	SYM
9878	150	82	A	A	NNP
9878	150	83	Validation	validation	NN
9878	150	84	Runtime	Runtime	NNP
9878	150	85	and	and	CC
9878	150	86	Conclusion	Conclusion	NNP
9878	150	87	Summary	Summary	NNP
9878	150	88	Appendix	Appendix	NNP
9878	150	89	A	a	NN
9878	150	90	:	:	:
9878	150	91	Sample	Sample	NNP
9878	150	92	TIFF	TIFF	NNP
9878	150	93	Metadata	Metadata	NNP
9878	150	94	with	with	IN
9878	150	95	ICC	ICC	NNP
9878	150	96	header	header	NN
9878	150	97	Appendix	Appendix	NNP
9878	150	98	B	B	NNP
9878	150	99	:	:	:
9878	150	100	Sample	Sample	NNP
9878	150	101	Code	Code	NNP
9878	150	102	to	to	TO
9878	150	103	convert	convert	VB
9878	150	104	PDF	PDF	NNP
9878	150	105	/	/	SYM
9878	150	106	A-2	A-2	NNP
9878	150	107	back	back	RB
9878	150	108	to	to	IN
9878	150	109	JPEG2000s	JPEG2000s	NNP
9878	150	110	References	reference	NNS