Bangla Handwritten Text Segmentation for Optical Character Recognition.

Date of Submission

December 1998

Date of Award

Winter 12-12-1999

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)


Chaudhuri, Bidyut Baran (CVPR-Kolkata; ISI)

Abstract (Summary of the Work)

This dissertation work puts forward, to be specific, two methods for segmentation of Bangla handwritten text into characters for Optical Character Recognition, OCR in brief. Given a text, we propose a method to segment words from text. Now, with each word we proceed towards its segmentation into characters. We detect different zones across the height of the word based on certain characteristics of Bangla writing methods. These zones give certain structural information about the respective word and its constituent characters. Thereafter, we approach segmentation of words into characters two methods are proposed. One based on vertical histogram and distance concepts, and the other one on recursive contour following and bounding box method. Limitations of these methods are also discussed with examples.


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.