Abstract: A computer vision edge-detection circuit uses two independent resistive networks to smooth the voltages supplied by an array of logarithmic photoreceptors. The voltages on the two networks are substracted and exclusive-or circuitry is used to detect zero-crossings. In order to facilitate thresholding of the edges, an additional current is computed at each node indicating the strength of the zero-crossing. This is particularly important for robust real-world performance where there will be many small zero-crossings induced by noise. Implementation of the present invention using analog VLSI techniques makes it feasible, and, in fact, practical to provide a large plurality of such photoreceptors on a single integrated circuit chip. Such chips can provide image acquisition and edge-detection with noise elimination in one chip in real time.