id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_ta5im6f32vgy3kyfnqnenznrry	D. Bertolini	Texture-based descriptors for writer identification and verification	2013	12	.pdf	application/pdf	9466	932	70	In this work, we discuss the use of texture descriptors to perform writer verification and identification. such as the impact of the number of references used for verification and identification, how the framework performs on the problem of writer identification, and how the dissimilarity-based approach compares to other feature-based strategies. of comprehensive experiments, we show that both LBPand LPQ-based classifiers are able to surpass previous results reported in the literature for the verification problem by about 5 percentage points. In Fig. 5a, Va, Vb, and Vc are the reference feature vectors extracted from the reference images (e.g. texture segments) for a given writer. The results for writer verification on the IAM database using different fusion rules Evolution of the number of texture images for identification – IAM database (R = 9). Texture-based descriptors for writer identification and verification Texture-based descriptors for writer identification and verification Texture-based descriptors for writer identification and verification	./cache/work_ta5im6f32vgy3kyfnqnenznrry.pdf	./txt/work_ta5im6f32vgy3kyfnqnenznrry.txt