A Segmentation Based Approach to Offline Handwritten Devanagari Word Recognition

1 December 2008

conference paper
conference paper
Published by Institute of Electrical and Electronics Engineers (IEEE)

p. 256-257
https://doi.org/10.1109/icit.2008.32

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

HANDWRITING RECOGNITION
SLABS
IMAGE SEGMENTATION
HEAD
PIXEL
INFORMATION TECHNOLOGY
HIDDEN MARKOV MODELS
IMAGE RECOGNITION
IMAGE QUALITY
PIECEWISE LINEAR TECHNIQUES

This publication has 2 references indexed in Scilit:

A Method for the Correction of Garbled Words Based on the Levenshtein Metric
IEEE Transactions on Computers, 1976
The String-to-String Correction Problem
Journal of the ACM, 1974

Cited by 19 articles