No abstract

I n any object recognition system a major and primary task is t o associate those image features, within an image of a complex scene, that arise from an individual object. The key idea here is that a geometric class defined in 3D induces relationships in the image which must hold between points on the image outline (the perspective projection of the object). The resulting image constraints enable both identification and grouping of image features belonging t o objects of that class.The classes include surfaces of revolution, canal surfaces (pipes) and polyhedra. Recognition proceeds by first recognising an object as belonging t o one of the classes (for example a surface of revolution) and subsequently identifying the object (for example as a particular vase). This differs f r o m conventional object recognition systems where recognition is generally targetted at particular objects. These classes also support the computation of SD invariant descriptions including symmetry axes, canonical coordinate frames and projective signatures.The constraints and grouping methods are viewpoint invariant, and proceed with no information on object pose. W e demonstrate the eflectiveness of this classbased grouping on real, cluttered scenes using grouping algorithms developed for rotationally symmetric surfaces, canal-surfaces and polyhedra.

No abstract

We demonstrate that viewpoint-invariant representations can be obtained from images for a useful class of 3D smooth object. The representations are stable over viewpoint, and also discriminate between different objects in the same class. They are computed using only image information, from the symmetry set of the object's outline. Examples are given of the representations obtained from real perspective images, and their use in a model-based recognition system for canal surfaces. 'The image outline of the surface.