Neural network modeling of new energy function for stereo matching
Jun-Jae Lee, Seok J. Cho, Yeong‐Ho Ha · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 1992
In vision research, most problems can be modeled as minimizing an energy function. Particularly, stereo matching can be viewed as one of the optimization problems in which the constraints must be satisfied simultaneously. Neural networks have been demonstrated to be very effective in computing these problems. In this paper, an approach to solve the stereo matching problem using the neural network with a new energy function is presented. The new energy function is derived not only to satisfy three constraints of similarity, smoothness, and uniqueness, but also to ensure Hopfield's convergence rules of symmetrical interconnection strength without self-feedback. Experimental results shows good stereo matching for sparse random dot stereograms and real images.