Geometric Aspects of Visual Object Recognition

Abstract
Systems (artificial or natural) for visual object recognition are faced with three fundamental problems: the correspondence problem, the problem of representing 3D shape, and the problem of defining a robust similarity measure between images and views of objects. In this thesis, I address each of these problems: I present a recognition algorithm (RAST) that works efficiently even when no correspondence or grouping information is given; that is, it works in the presence of large amounts of clutter and with very primitive features. I discuss representations of 3D objects as collections of 2D views for the purposes of visual object recognition. Such representations greatly simplify the problems of model acquisition and representing complex shapes. I present theoretical and empirical evidence that this view-based approximation is an efficient, robust, and reliable approach to 3D visual object recognition. I present Bayesian and MDL approaches to the similarity problem that may help us build more robust recognition systems.... Computer vision, Point matching, Bounded error, 3D Object recognition.

This publication has 0 references indexed in Scilit: