Cellular Neural Network in Gray-scale Video Traffic Image Processing

Abstract—Cellular neural network (CNN) is a large-scale nonlinear analog circuit suitable for real-time signal and image processing ． In this paper，the CNN is applied in order to detect edges of gray-scale video traffic images. Edges are an important character to feature extraction of the images. Based on Matlab 7.0, the experimental results, compared with the traditional edge detection algorithm Canny, show that CNN can not only be available but quickly detect the complete image edges. This paper also proposes an effective way to eliminate the false edges and deduces the range of CNN template parameters. The results presented show that this approach is valid． Index Terms—Cellular neural network, Edge detection