In Proceedings of ICCV ' 95 Invariant - Based Recognition of Complex Curved 3 D Objects

To recognize three-dimensional objects bounded by smooth curved surfaces from monocular image contours , viewpoint-dependent image features must be related to object geometry. Contour bitangents and in-ections along with associated parallel tangents points are the projection of surface points that lie on the oc-cluding contour for a ve-parameter family of scaled orthographic projection viewpoints. An invariant representation can be computed from these image features and used for modeling and recognizing objects. Mod-eling is achieved by moving an object in front of a camera to obtain a curve of possible invariants. The relative camera-object motion is not required, and 3D models are not utilized. At recognition time, invari-ants computed from a single image are used to index the model database. Using the matched features, independent qualitative and quantitative veriication procedures eliminate potential false matches. Examples from an implementation are presented.