EDGE DETECTION USING CELLULAR NEURAL NETWORK AND TEMPLATE OPTIMIZATION

Result of edge detection using CNN could be not optimal, because the optimal result is based on template applied to the images. During the first years after the introduction of the CNN, many templates were designed by cut and try techniques. Today, several methods are available for generating CNN templates or algorithms. In this paper, we presented a method to make the optimal result of edge detection by using TEMPO (Template Optimization). Result shown that template optimization improves the image quality of the edges and noise are reduced. Simulation for edge detection uses CANDY Simulator, then we implementing the program and optimized template using MATLAB. Comparing to Canny and Sobel operators, image shapes result from CNN edge detector also show more realistic and effective to user