Image segmentation using genetic algorithm and morphological operations

This thesis presents an image segmentation procedure that uses genetic algorithm and mathematical morphology for optimizing a criterion function. The image is divided into subimages and segmentation algorithm is applied to each subimage, starting with initial random populations. Each individual of the population is evaluated using an a fitness function. The best-fit individuals are selected and mated to produce offsprings that form the next generation. The morphological operation is used to produce the next generation along with the crossover and mutation operators. The algorithm converges to yield the segmented subimages. These segmented subimages then are combined to form the final result. The performance of genetic algorithm and morphological operations to an image segmentation problem is evaluated with respect to various parameters and the results are presented and discussed.