Online Handwritten Bangla Character Recognition.

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

Department

Computer Vision and Pattern Recognition Unit (CVPR-Kolkata)

Supervisor

Garain, Utpal (CVPR-Kolkata; ISI)

Abstract (Summary of the Work)

Handwritten text is a common, natural form of communication for humans. Therefore, as a useful means of input to machines, this mode can be utilized. This thesis deals with the online handwriting recognition system for Bangla script. A template-based recognition system is demonstrated here. An efficient classifier has been designed and a similarity measure, which is quite robust against wide varieties of writing styles, has been proposed. The method has been initially applied for recognition of characters in Bangla script. Our classifier achieves an overall 96.34% accuracy on a dataset of considerable size alphanumeric characters (60 classes - 10 numerals, 29 full letters, 12 parts of a letter and 9 vowel marker).

Comments

ProQuest Collection ID: http://gateway.proquest.com/openurl?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:dissertation&res_dat=xri:pqm&rft_dat=xri:pqdiss:28843257

Control Number

ISI-DISS-2002-90

Creative Commons License

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

DOI

http://dspace.isical.ac.in:8080/jspui/handle/10263/6262

This document is currently not available here.

Share

COinS