Abstract
Pixel correspondence is an important problem in stereo vision, motion, structure from motion, etc. Several procedures have been proposed in the literature for this problem, using a variety of image features to identify the corresponding features. Di erent features work wel l under di erent conditions. An algorithm that can seamlessly integrate multiple features in a flexible manner can combine the advantages of each. We propose a framework to combine heterogenous features, each with a di erent measure of importance, into a single correspondence computation in this paper. We also present an unsupervised procedure to select the optimal combination of features for a given pair of images by computing the relative importances of each feature. A unique aspect of our framework is that it is independent of the speci c correspondence algorithm used. Optimal feature selection can be done using any correspondence mechanism that can be extended to use multiple features. We also present a few examples that demonstrate the e ectiveness of the feature selection framework.
