Online Character Recognition Using Hidden Markov Model.

Date of Submission

December 2002

Date of Award

Winter 12-12-2003

Institute Name (Publisher)

Indian Statistical Institute

Document Type

Master's Dissertation

Degree Name

Master of Technology

Subject Name

Computer Science


Computer Vision and Pattern Recognition Unit (CVPR-Kolkata)


Garain, Utpal (CVPR-Kolkata; ISI)

Abstract (Summary of the Work)

Nowadays people are interested to interact with computers in their local languages. It is very tedious task to make keyboard for all existing characters and their combinations. Users will be more comfortable to input characters as handwritten rather than keying-in.The widely accepted approach for online character recognition is to capture a character as a sequence (x(t), y(t)) of points while the character is being written on a digitizer tablet using a pen kind of tool.This is the only information available for a character. Each point of the sequence can be coded as a finite set of features like direction, pen-ups, velocity of the pen etc. ... Different people have used different features. We have used direction code and length of the segment.There are many different methods have been proposed for character recognition. We have used Hidden Markov Model( HMM) to recognize a character.


ProQuest Collection ID:

Control Number


Creative Commons License

Creative Commons Attribution 4.0 International License
This work is licensed under a Creative Commons Attribution 4.0 International License.


This document is currently not available here.