A new approach for color image edge detection using improved PCNN

Recent researches indicate that pulse coupled neural network can be implemented on image processing, such as image segmentation and edge detection effectively. However, up to now it has mainly been used in the processing of gray images or binary images, and the parameters of the network are always adjusted and confirmed manually for different images, which impede PCNN's application in image processing. To solve the problem, this paper use PCNN in the color image se-mentation with the parameters determined by images' spatial and gray characteristics automatically at the first then use the above method to obtaine the edge information. The experiment results shows its validity and robustness.