Stereo correspondence using Hopfield network with multiple constraints

The paper proposes an algorithm to solve the difficult problem of stereo correspondence in stereo vision. This problem can be considered as an optimization process or a constraint satisfaction process. It is found that in the course of the constraint satisfaction process, the more constraints the cost function specifies, the more accurate the result will be. The authors propose a similarity constraint coupled with the uniqueness, smoothing, ordering constraints to formulate the energy function of a Hopfield network to perform the optimum task. Simulation results have verified the effectiveness of our approach.