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.

Pulse coupled neural network (PCNN) has a specific feature that the fire of one neuron can capture its adjacent neuron to fire due to their spatial proximity and intensity similarity. In this paper, it is indicated that this feature itself is a very good mechanism for image filtering when the image is damaged with pet and salt type noise (PASN). An adaptive filtering method, in which the noisy pixels are first located and then filtered based on the output of the PCNN is presented. The threshold function of a neuron in the PCNN is designed for random PASN and extreme PASN contaminated image respectively. The filtered image has no distortion for noisy pixels and only less mistiness for non-noisy pixels, compared with the conventional window-based filtering method. Excellent experimental results show great effectiveness and efficiency of the proposed method, especially for the heavily noise contaminated images.