Abstract

The problem of establishing image-to-image correspondences is fundamental in computer vision. Recently,several wide baseline matching algorithms capable of handling large changes of viewpointhaveap peared. By computing feature values from image data, these algorithms mainly use appearance as a cue for matching. Topological information, i.e. spatial relations between features, has also been used, but not nearly to the same extent as appearance. In this paper, we incorporate topological constraints into an existing matching algorithm [1] whichma t c hes image intensity proÿles between interest points. Weshowthat the algorithm can be improved by exploiting the constraint that the intensity proÿles around eachinterest point should be cyclically ordered. String matching techniques allows for an eÆcient implementation of the ordering constraint. Experiments with real data indicate that the modiÿed algorithm indeed gives superior results to the original one. The method of enforcing the spatial constraints is not limited to the presented case, but can be used on any algorithm where interest point correspondences are sought