Geometric Invariants and Object Recognition.
MARYLAND UNIV COLLEGE PARK CENTER FOR AUTOMATION RESEARCH
Pagination or Media Count:
In this paper we discuss the role of the general invariance concept in object recognition, and review the classical and recent literature on projective invariance. Invariants help solve major problems of object recognition. For instance, different images of the same object often differ from each other, because of the different viewpoint from which they were taken. To match the two images, common methods thus need to find the correct viewpoint, a difficult problem that can involve search in a large parameter space of all possible points of view andor finding point correspondences. Geometric invariants are shape descriptors, computed from the geometry of the shape, that remain unchanged under geometric transformations such as changing the viewpoint. Thus they can be matched without search. Deformations of objects are another important class of changes for which invariance is useful.