Open-close by reconstruction on CNNUM

Open-close by reconstruction is one of the most important algorithms in mathematical morphology. It is used widely in image and video processing, but it requires the huge computational power, what is the bottleneck for application. So in this paper, cellular neural network (CNN) is used to solve the problem, new +1 template and "and" template are designed here. Along with the already developed templates and image preprocessing technique, the gray-scale open-close by reconstruction is realized. Experimental results based on CNN simulator are shown, proved that the speed on CNN is about 300 times faster than in traditional PC, the real time processing can be realized.