Optical Character Recognition for Indian Language Scripts Using Support Vector Machines.

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

Mitra, Mandar (CVPR-Kolkata; ISI)

Abstract (Summary of the Work)

In this study we investigate the use of Support Vector Machi.s(SVM) for optical character recognition in an Indian language (Bangla). We start with a state of the art system that achieves fairly high accuracy. Weidentify some pairs of characters frequently confused by the current system. SVM are used to distinguish these pairs. The SVM based classifier performs significantly better than the existing classifier for these pairs of characters. Preliminary at- tempts to use SVMS as a general classsifier for all classes have yielded disappointing results and further investigation is necessary.

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:28843244

Control Number

ISI-DISS-2002-98

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/10263/6270

This document is currently not available here.

Share

COinS