Corner Detection in Binary and Gray Images using Neural Network.

Date of Submission

December 1999

Date of Award

Winter 12-12-2000

Institute Name (Publisher)

Indian Statistical Institute

Document Type

Master's Dissertation

Degree Name

Master of Technology

Subject Name

Computer Science


Machine Intelligence Unit (MIU-Kolkata)


Basak, Jayanta (MIU-Kolkata; ISI)

Abstract (Summary of the Work)

In this dissertation, neural network based methodologies are developed for the detection of corner points in both binary and gray images. For a given binary/gray image, each pixel in the image is assigned with some initial cornerity (our measurable quantity) which is a vector repensenting the direction and strength of the corner. These corneritis are then mapped onto a neural network model which is essentially designed as a cooperative computational framework. A pair of neurons in the network model corresponds to a pixel in the image. The cornerity at each pixel position (i.e., at each pair of neurons) is updated according to the corneritis at the surrounding locations (i.e., the neighborhood information). The actual corner points are obtained after the network dynamics settles to stable state. Theoretical investigations are made to ensure the stability and convergence of the network. It is found that the network is able to detect corner points even in the noisy images and for open object boundaries. The dynamics of the network is extended to accept the edge information from gray images also. The effectiveness of the model is experimentally demonstrated in synthetic and real-life binary and gray images.


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.