Multiple feature models for image matching

Abstract

The common approach to image matching is to detect spatial features present in both images and create a mapping that relates both images. The main draw back of this method takes place when more than one matching is likely. A first simplification to this ambiguity is to represent with apara-metric model the point locus where the matching is highly likely,and then use a POCS(projection on to convex sets)procedure combined with Tikhonov regularization that results in the mapping vectors. However,if there is more than one model perpixel,the regularization and constrainforcing process faces a multiplechoice dilemma that has no easy solution. This work proposes a frame work to overcome this draw back: the combined projection over multiple models base don the norm of the projection–pointdis-tance. This approach is tested on a stereo-pair that presents multiple choices of similar likelihood.