Low-level image processing and edge enhancement using a self-organizing neural network

A self-organizing artificial neural network has been described to enhance and restore gray-level images for applications in low-level image processing. The image is described by a set of interconnected neurons with their values equal to the gray-level values of corresponding pixels. The first-order and second-order contrast links are defined among the neurons which are analyzed for a change in their values in the adaptive constrained environment. Each selected neuron is analyzed only once per iteration, in which its value may be readjusted by incrementing or decrementing the current value. As a result, at the end of each iteration the image data is reorganized. The structure and algorithm of the proposed neural network are presented along with various experimental results showing the capability of such a network to restore and enhance the gray-level images