Image matching based on tracking matching paths in the similarity space

In this paper, we explore the feasibility of implementing surface continuit y and ordering constraints by tracking connected local peak points in the s pace of matching similarity. We present a new image matching algorithm base d on match paths directly extracted in the similarity space. The main advan tage of these kinds of tokens over tokens extracted from the left and right images is that the geometric distortions ca used by perspective effects an d description inconsistency caused by independent extraction of tokens in t he left and right images are automatically eliminated. Through the tracking process, the computation is greatly reduced. In addition, global informati on available to support a local match for resolving matching ambiguities is fully utilized in such a way that unrelated global information is excluded . Thus, the new image matching algorithm is reliable and efficient. By elim inating the interpolation process at the levels except the finest, the occl uded regions and depth discontinuities can be well localized.