Artificial neural networks are designed to detect edges and extract edges. The system can accomplish the following tasks : (a) obtain enhanced edges; (b) recover missing edges; (c) eliminate false edges caused by noise. The research comprises two phases, namely, edge detection by a fuzzy neural net and edge enhancement by a modified Hopfield neural network. The proposed fuzzy neural network is trained by typical patterns to enable it to determine the edge elements with eight orientations, and to provide the edge measurement for further processing. A modified Hopfield net is proposed to enhance edge measurement. Based on constraint satisfaction and the competitive mechanism, interconnection between neural cells are determined. A criteria is provided to find the final stable result which contains the enhanced edge measurement.