Stereo-disparity estimation using a supervised neural network

We deal with the problem of determining disparity in gray-level stereoimage-pairs, by treating it as a nonlinear classification problem, and invoking Marr and Poggio's [1] neighborhood criterion. To this end, we propose the application of an artificial neural network (ANN). The main contribution of the paper is believed to be the use of neurons which are trained to be disparity selective, and thereby dispensing with the standard assumptions made about the neighborhood. The disparity estimates so obtained for random-dot and natural stereoimage-pairs are comparable to those found in the literature. Whereas Khotanzad et al. [3] used a multi-layer perceptron (MLP) in order to learn the constraints of a cooperative stereo algorithm for binary, random-dot stereograms, we employ a single layer ANN. Further, in our scheme, the ANN weights adapt themselves to the neighborhood, and are able to learn the constraints successfully.