Edge detection in noise mounted picture

This work presents cellular neural networks (CNN), where the output of an object gives edge detection. First, the output which is detected is used in the training set. Then the original picture is changed with noise. After training, CNN is applied to the changed picture. These templates which are taken from the first training are provided from the simple picture. Then the templates are used on the other complex picture. Second, the output of the complex picture is used in the training set for the edge detection of the noisy picture. Last, the output of the complex picture is prepared manually. This output is used in the training set then the edge of the complex picture is detected.