A modification of de CNN model is proposed in this work. An iterated-map is defined instead of the original differential equation while a sigmoid function is taken as the cell output. Modifications in the structure and values of the synaptic scheme alow the use of the model in different task. The network behaviour is mainly determined by its feedforward term, while feedback simply adds optimization to the network's output. The network's stability is discussed. Edge detection and contrast enhancement performed, stressing the fact that are only different aspects of the same network property: the enhancement ofbrightness gradients. Some examples are presened in which grey scale images are processed, revealing the capabiities of the model both in detecting edges and in enhancing contrasts.