In order to improve effect of color image segmentation

a color image segmentation method based on pulse coupled neural network（ PCNN） combined with the maximum gray entropy image component is proposed. In the presented method

the color image is converted to HSV color space which is consistent with visual features of human eyes; the component with the largest image entropy is selected for image enhance by PCNN to increase the contrast of the region of interest; the enhanced component of the image is used to be segmented by PCNN

and the loop of PCNN is terminated when the two dimensional Renyi entropy value for the segmented image is not larger than the previous one

terminate cyclic segmentation to get the optimal segmentation result. The segmentation results are evaluated by using several commonly used evaluation criteria

and show that the segmentation of color image can be realized efficiently by the proposed algorithm with more clear details of the image than by the traditional color image segmentation method.