Dealing with occlusions in the eigenspace approach

The basic limitations of the current appearance-based matching methods using eigenimages are non-robust estimation of coeecients and inability to cope with problems related to occlusions and segmentation. In this paper we present a new approach which successfully solves these problems. The major novelty of our approach lies in the way how the coeecients of the eigenimages are determined. Instead of computing the coeecients by a projection of the data onto the eigeni-mages, we extract them by a hypothesize-and-test paradigm using subsets of image points. Competing hypotheses are then subject to a selection procedure based on the Minimum Description Length principle. The approach enables us not only to reject outliers and to deal with occlusions but also to simultaneously use multiple classes of eigenimages. We are also grateful to V. Hlavv a c and T. Pajdla for discussions.