Robust Design for Generalized Point Extract CNN with Application in Image Processing

The cellular neural/nonlinear network (CNN) is a powerful tool for image and video signal processing, as well as robotic and biological visions. The designs for CNN templates are one of the important issues for the practical applications of CNNs. This paper first describes and proves the local rules of the binary Point Extract (PE) CNN introduced by Roska et al., then extends the PE CNN to a gray similar neighborhood pixel remover (SNPR) CNN. The robust design theorem of the SNPR CNN has been established, using a PE CNN and a SNPR processes several images. The results agree with theoretical predictions. In particular, combining the SNPR CNN with median filtering approach is able to remove the salt & pepper noise in images.