Abstract: In this paper we propose a new approach to solve the correspondence problem for a set of segments extracted from a pair of stereo images. The problem is first formulated as an optimization task where a cost function, which represents the constraints on the solution, is to be minimized. The optimization problem is then performed by a two-dimensional Hopfield neural network. The network uses several local constraints like correlation, and compatibility measures between segments of a pair stereo images. Finally we show numerous results obtained with this approach.