A morphological approach for text-line segmentation in handwritten documents

Papavassiliou, V; Katsouros, V; Carayannis, G

dc.contributor.author	Papavassiliou, V	en
dc.contributor.author	Katsouros, V	en
dc.contributor.author	Carayannis, G	en
dc.date.accessioned	2014-03-01T02:52:32Z
dc.date.available	2014-03-01T02:52:32Z
dc.date.issued	2010	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/35920
dc.subject.other	Binary morphology	en
dc.subject.other	Data sets	en
dc.subject.other	Document image segmentation	en
dc.subject.other	Efficient method	en
dc.subject.other	Handwriting segmentation	en
dc.subject.other	Handwritten document	en
dc.subject.other	Line segmentation	en
dc.subject.other	Line structures	en
dc.subject.other	Morphological approach	en
dc.subject.other	Morphological operations	en
dc.subject.other	Overlapping regions	en
dc.subject.other	Printed documents	en
dc.subject.other	Processing machines	en
dc.subject.other	Rank-order filtering	en
dc.subject.other	Text lines	en
dc.subject.other	Vertical direction	en
dc.subject.other	Digital image storage	en
dc.subject.other	Feedforward neural networks	en
dc.subject.other	Image segmentation	en
dc.subject.other	Mathematical morphology	en
dc.subject.other	Character recognition	en
dc.title	A morphological approach for text-line segmentation in handwritten documents	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/ICFHR.2010.11	en
heal.identifier.secondary	http://dx.doi.org/10.1109/ICFHR.2010.11	en
heal.identifier.secondary	5693494	en
heal.publicationDate	2010	en
heal.abstract	Document image segmentation to text lines is a critical stage towards unconstrained handwritten document recognition. Although morphological operations proved to be effective in processing machine-printed documents for several issues, similar methods for unconstraint-handwritten documents lack accuracy. We propose an efficient method based on binary morphology for text-line segmentation in such documents. The basic steps of our approach are: a) subsampling and binary rank order filtering to enhance the text-line structures and b) applying dilations and (p,q)-th generalized foreground rank openings successively to join close and horizontally overlapping regions while preventing a merge in the vertical direction. The method tested on the benchmarking dataset of the ICDAR07 handwriting segmentation contest and show remarkable results. © 2010 IEEE.	en
heal.journalName	Proceedings - 12th International Conference on Frontiers in Handwriting Recognition, ICFHR 2010	en
dc.identifier.doi	10.1109/ICFHR.2010.11	en
dc.identifier.spage	19	en
dc.identifier.epage	24	en