Stereopsis by constraint learning feed-forward neural networks

Abstract

A neural network (NN) approach to the problem of steropsis is presented. The correspondence problem (finding the correct matches between pixels of the epipolar lines of the stereo pair from among all the possible matches) is posed as a noniterative many-to-one mapping. Two multilayer feedforward NNs are utilized to learn and code this nonlinear and complex mapping using the backpropagation learning rule and a training set. The first NN is a conventional fully connected net while the second is a sparsely connected NN with a fixed number of hidden layer nodes. All the applicable constraints are learned and internally coded by the NNs enabling them to be more flexible and more accurate than previous methods. The approach is successfully tested on several random-dot stereograms. It is shown that the nets can generalize their learned mappings to cases outside their training sets and to noisy images. Advantages over the Marr-Poggio algorithm are discussed, and it is shown that the NNs performances are superior.