LOCAL PROJECTIVE AND AFFINE INVARIANTS

We present a new and more robust method of obtaining local projective and affine invariants. These shape descriptors are useful for object recognition because they eliminate the search for the unknown viewpoint. Being local, our invariants are much less sensitive to occlusion than the global ones used elsewhere. The basic ideas are: (i) employing an implicit curve representation without a curve parameter, to increase robustness; (ii) using a canonical coordinate system which is defined by the intrinsic properties of the shape, independently of the given coordinate system, and is thus invariant. Several configurations are treated: a general curve without any correspondence, and curves with known correspondences of one or two feature points or lines.