A Method of Color Image Segmentation Based on DPCNN

A method of color image segmentation is proposed based on double pulse-coupled neural networks (DPCNN) in this paper. First, color quantization is performed on the color images in the HSI color pattern. Then the method uses the result of color quantization as the input of DPCNN to form the initial segmented regions. Finally, the initial regions are merged based on the region distance defined by the color and spatial information. A rule here is given to decide the termination of merging process. The method can segment image edge properly and effective which is shown by the experiment results.