Title :
A Segmentation Based Approach to Offline Handwritten Devanagari Word Recognition
Author :
Shaw, Bikash ; Parui, Swapan Kumar ; Shridhar, Malayappan
Author_Institution :
Indian Stat. Inst., Kolkata, India
Abstract :
The present paper proposes a segmentation-based approach to handwritten Devanagari word recognition. On the basis of the head line, a word image is segmented in to pseudo characters. Hidden Markov models are proposed to recognize the pseudo characters. The word level recognition is done on the basis of a string edit distance.
Keywords :
handwritten character recognition; hidden Markov models; image segmentation; hidden Markov models; offline handwritten Devanagari word recognition; segmentation based approach; string edit distance; Handwriting recognition; Head; Hidden Markov models; Image quality; Image recognition; Image segmentation; Information technology; Piecewise linear techniques; Pixel; Slabs;
Conference_Titel :
Information Technology, 2008. ICIT '08. International Conference on
Conference_Location :
Bhubaneswar
Print_ISBN :
978-1-4244-3745-0
DOI :
10.1109/ICIT.2008.32
