id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_yb2mzleh2rdpbgrztb2m5gw7fy	Ofer Biller	Evolution maps and applications	2016	20	.pdf	application/pdf	6984	997	23	employed to improve state of the art binarization algorithm, and achieve automatically character size estimation, line extraction, stroke width estimation, and feature We then utilize this information to improve state-of-the-art binarization, line segmentation, and characterizing feature behavior in a document collection. For a given property of the connected components in a document, the evolution maps document analysis algorithms, such as binarization and line extraction, provide poor Figure 1 A document image, and the distribution of connected components along their width property (x-axis), for each possible gray scale threshold (y-axis). represents the width CEM for a text document image, where 'hot' colors represent high threshold, and the corresponding components in the document for two ranges of width Figure 5 A document image with its components according to the width evolution map. Figure 11 (A) A document and (B) its stroke width evolution map. line segmentation in degraded documents, stroke width estimation, and analysis of	./cache/work_yb2mzleh2rdpbgrztb2m5gw7fy.pdf	./txt/work_yb2mzleh2rdpbgrztb2m5gw7fy.txt