Lexicon-free, novel segmentation of online handwritten indic words

Sundaram, Suresh and Ramakrishnan, AG (2011) Lexicon-free, novel segmentation of online handwritten indic words. In: 2011 International Conference on Doocument Analysis and Recognition (ICDAR), 18-21 Sept. 2011, Beijing, China.

PDF Doo_Ana_Rec_1175_2011.pdf - Published Version Restricted to Registered users only Download (247kB) | Request a copy

Abstract

Research in the field of recognizing unlimited vocabulary, online handwritten Indic words is still in its infancy. Most of the focus so far has been in the area of isolated character recognition. In the context of lexicon-free recognition of words, one of the primary issues to be addressed is that of segmentation. As a preliminary attempt, this paper proposes a novel script-independent, lexicon-free method for segmenting online handwritten words to their constituent symbols. Feedback strategies, inspired from neuroscience studies, are proposed for improving the segmentation. The segmentation strategy has been tested on an exhaustive set of 10000 Tamil words collected from a large number of writers. The results show that better segmentation improves the overall recognition performance of the handwriting system.

Item Type:	Conference Proceedings
Publisher:	IEEE
Additional Information:	Copyright of this article belongs to IEEE.
Keywords:	Dominant Overlap Segmentation (DOS); Feedback Segmentation (FS; Online Tamil Symbol Recognition; Stroke Group; Support Vector Machine (SVM)
Department/Centre:	Division of Electrical Sciences > Electrical Engineering
Date Deposited:	23 Apr 2013 06:27
Last Modified:	23 Apr 2013 06:27
URI:	http://eprints.iisc.ac.in/id/eprint/46232

Actions (login required)

View Item