ASelf-Adaptive HybridGenetic Algorithm forColorClustering

Abstract Color palettes are inherent to color quantizedimagesandrepresenttherangeofpossible colorsin suchimages.When converting full true color images to palletized counterparts, the color palette should be chosen so as tominimize the resulting distortion compared to the original. Inthis paper, weshowthat in contrast to previous approaches oncolor quantization, which rely on either heuristics or clustering techniques, a generic optimization algorithm such as a self-adaptive hybrid genetic algorithm can be employed togenerate a palette of high quality. Experiments on a set ofstandard test images using a novel self-adaptive hybrid genetic algorithm showthat this approach is capable of outperforming several conventional color quantization algorithms and providesuperiorimagequality. I. INTRODUCTION True color images typically use 24 bits per pixel whichresults in an overall gamutof224 i.e. more than 16.8 milliondifferent colors. While nowadays most images are captured andstored in that format,