Skeletonizing Binary Images Using Neural Networks.

Date of Submission

December 1992

Date of Award

Winter 12-12-1993

Institute Name (Publisher)

Indian Statistical Institute

Document Type

Master's Dissertation

Degree Name

Master of Technology

Subject Name

Computer Science

Department

Computer and Statistical Services Centre (CSSC)

Supervisor

Dutta, Amitabha (CSSS-Kolkata; ISI)

Abstract (Summary of the Work)

The project aims at developing an incremental neural network model which is able to learn a stick figure of a given image . Some of the ideas are similar to those in Growing Neural Gas model by Bernd Fritzke which learns the topologies of a data distribution P(C) . At first, it has been shown that a different criterion for growth of the network ( which we have called Vote Counting Method) has the same performance as Growing Neural Gas model. Then we have introduced a different approach to growth which learns a stick figure of a given image.

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:28843096

Control Number

ISI-DISS-1992-169

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/10263/6337

This document is currently not available here.

Share

COinS