Color image segmentation by a genetic algorithm based clustering and Connected Component Labeling

In this paper, we present a two steps segmentation method. The first consists in color image quantization by genetic algorithm based clustering method where variable string length and fitness function with a smallest number of variables are used. Once pixels are classified in 3D color space, a Connected Component Labeling adapted to color image is proposed and applied to the 2D image space to get separate regions. Results are discussed using Berkeley color images base in RGB and Lab color spaces.