Three-Dimensional Object Recognition Using an Unsupervised Neural Network: Understanding the Distinguishing Features
Nathan Intrator, Bülthoff Gold Ji, Shimon Edelman, Y. Feldman A. Bruckstein · 1991
A novel method for feature extraction has been applied to a problem of three-dimensional object recognition (Intrator and Gold, 1991). The method is related to recent statistical theory (Huber, 1985; Friedman, 1987) and is derived from a biologically motivated computational theory (Bienenstock et al., 1982). Results of an initial study replicating recent psychophysical experiments (Bulthoff and Edelman, 1990) demonstrated the utility of the proposed method for feature extraction. We describe further experiments designed to analyze the nature of the extracted features, and their relevance to the theory and psychophysics of object recognition. Research was supported by the National Science Foundation, the Army Research Office, and the Office of Naval Research. 1 Introduction Object recognition may be accomplished via a comparison between an image and a set of templates that represent known objects. However, since the number of different objects that are to be recognized --- includin...