Skip to Main Content
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.