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 segmentation 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.

[1]  Dai Ruo-lan,et al.  Automated image segmentation using pulse coupled neural networks and images entropy , 2002 .

[2]  Daoheng Yu,et al.  A new approach for automated image segmentation based on unit-linking PCNN , 2002, Proceedings. International Conference on Machine Learning and Cybernetics.

[3]  Manfred Opper,et al.  Region growing with pulse-coupled neural networks: an alternative to seeded region growing , 2002, IEEE Trans. Neural Networks.

[4]  John L. Johnson,et al.  PCNN models and applications , 1999, IEEE Trans. Neural Networks.

[5]  Liu Qing,et al.  Automated image segmentation using improved PCNN model based on cross-entropy , 2004, Proceedings of 2004 International Symposium on Intelligent Multimedia, Video and Speech Processing, 2004..

[6]  De Xu,et al.  Proceedings of the 7th WSEAS International Conference on Simulation, Modelling and Optimization , 2007 .