Abst rac t . This paper describes an experimental investigation of the recognition performance of two approaches to the representation of objects for recognition. The first representation, generally known as appearance modelling, describes an object by a set of images. The image set is acquired for a range of views and illumination conditions which are expected to be encountered in subsequent recognition. This image database provides a description of the object. Recognition is carried out by constructing an eigenvector space to compute efficiently the distance between a new image and any image in the database. The second representation is a geometric description based on the projected boundary of an object. General object classes such as planar objects, surfaces of revolution and repeated structures support the construction of invariant descriptions and invariant index functions for recognition. In this paper we present an investigation of the relative performance of the two approaches. Two objects, a planar object and a rotationally symmetric object are modelled using both approaches. In the experiments, each object is intentionally occluded by an unmodelled distractor for a range of viewpoints. The resulting images are submitted to two separate recognition systems. Appearance-based recognition is carried out by SLAM and recognition of invariant geometric classes by Lewis/Morse.
Download Full PDF Version (Non-Commercial Use)