By Topic

A Fast Time Scale Genetic Algorithm based Image Segmentation using Cellular Neural Networks (CNN)

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

6 Author(s)
S. SanthoshKumar ; Dept. of Electron. & Commun. Eng., Sri Venkateswara Coll. of Eng., Sriperumbudur ; J. Vignesh ; L. R Rangarajan ; V Shankar Narayanan
more authors

We present a novel approach for image segmentation using genetic algorithm (GA) implemented in cellular neural networks (CNNUM). This paper also demonstrates how the cellular neural universal machine architecture can be extended to image segmentation. It uses the highly parallel nature of the CNN structure and its speed outperforms traditional digital computers. The GA starts with a population of solutions, initialized randomly, to represent possible solutions of the segmentations. The solutions are evaluated using an appropriate fitness function and the fittest candidates are selected to be parents for producing off springs that form the next generation over several generations, populations evolve to yield the optimal results. The simulation results indicate that the quality of the segmented image is improvised by genetic algorithm using CNN in a time efficient manner. The feasibility of applying GA using CNN to image segmentation is investigated and initial results of segmentation of images are presented.

Published in:

Signal Processing and Communications, 2007. ICSPC 2007. IEEE International Conference on

Date of Conference:

24-27 Nov. 2007