Abstract not found

In human vision, the processes and the representations involved in identifying specific individuals are frequently assumed to be different from those used for basic-level classification, because classification is largely viewpoint-invariant, but identification is not. This assumption was tested in psychophysical experiments, in which objective similarity between stimuli (and, consequently, the level of their distinction) varied in a controlled fashion. Subjects were trained to discriminate between two classes of computer generated 3D objects, one resembling monkeys, and the other dogs. Both classes were defined by the same set of 56 parameters, which encoded sizes, shapes, and placement of the limbs, the ears, the snout, etc. Interpolation between parameter vectors of the class prototypes yielded shapes that changed smoothly between monkey and dog. Within-class variation was induced in each trial by randomly perturbing all the parameters. After the subjects reached 90% correct performa...

Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works, must be obtained from the IEEE. Contact: Manager,

This paper sketches several aspects of a hypothetical cortical architecture for visual object recognition, based on a recent computational model. The scheme relies on modules for learning from examples, suchas Hyperbf-likenetworks, as its basic components. Such models are not intended to be precise theories of the biological circuitry but rather to capture a class of explanations we call Memory-Based Models (MBM) that contains sparse population coding, memory-based recognition and codebooks of prototypes. Unlike the sigmoidal units of some artificial neural networks, the units of MBMs are consistent with the usual description of cortical neurons as tuned to multidimensional optimal stimuli. We will describe howan example of MBM may be realized in terms of cortical circuitry and biophysical mechanisms, consistent with psychophysical and physiological data. A number of predictions, testable with physiological techniques, are made.

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...

Computational or information-processing theories of vision describe object recognition in terms of a comparison between the input image and a set of stored models that represent known objects. The nature of these representations is reflected in the performance of the visual system and may be studied experimentally, by presenting subjects with computer graphics simulations of three-dimensional objects (with precisely controlled shape cues), and by analyzing the ensuing patterns of response time and error rate. We discuss a series of psychophysical experiments that explore different aspects of the problem of subordinate-level object recognition and representation in human vision. Contrary to the paradigmatic view which holds that the representations are three-dimensional and object-centered, the results consistently support the notion of view-specific representations that include at most partial depth information. In simulated experiments that involved the same stimuli that were shown to...

Introduction The appearance of a three-dimensional object (that is, the pattern formed by its projection onto the retina of an eye or onto the imaging plane of a camera) depends on the point of view of the observer. The collective human awareness of this dependence is attested to by the widespread use of expressions that involve the metaphor of point of view, in languages as different as English, Russian, and Hebrew. Nevertheless, as far as recognition is concerned, the matters of viewpoint seem to be of secondary importance: the human visual system exhibits an impressive ability to recognize a familiar object viewed from an unfamiliar perspective. This phenomenon has been termed shape constancy, by analogy with other perceptual constancies. 1 Computational understanding of shape constancy can be gained both by attempting to build artificial vision systems for object recognition, and by modeling human performance in this task. Maintaining a const

This paper describes the main features of a view-based model of object recognition. The model tries to capture general properties to be expected in a biological architecture for object recognition. The basic module is a regularization network in which each of the hidden units is broadly tuned to a specific view of the object to be recognized. The network output, which may be largely view independent, is first described in terms of some simple simulations. The following refinements and details of the basic module are then discussed: (1) some of the units may represent only components of views of the object -- the optimal stimulus for the unit, its "center", is effectively a complex feature; (2) the units' properties are consistent with the usual description of cortical neurons as tuned to multidimensional optimal stimuli; (3) in learning to recognize new objects, preexisting centers may be used and modified, but also new centers may be created incrementally so as to provide maximal inva...

Theories of object recognition often assume that only one representation scheme is used within one visual-processing pathway. Versatility of the visual system comes from having multiple visual-processing pathways, each specialized in a different category of objects. We propose a theoretically simpler alternative, capable of explaining the same set of data and more. A single primary visual-processing pathway, loosely modular, is assumed. Memory modules are attached to sites along this pathway. Object-identity decision is made independently at each site. A site's response time is a monotonic-decreasing function of its confidence regarding its decision. An observer's response is the first-arriving response from any site. The effective representation(s) of such a system, determined empirically, can appear to be specialized for different tasks and stimuli, consistent with recent clinical and functional-imaging findings. This, however, merely reflects a decision being made at its appropriate level of abstraction. The system itself is intrinsically flexible and adaptive.

Intrator (1990) proposed a feature extraction method that is related to recent statistical theory (Huber, 1985; Friedman, 1987), and is based on a biologically motivated model of neuronal plasticity (Bienenstock et al., 1982). This method has been recently applied to feature extraction in the context of recognizing 3D objects from single 2D views (Intrator and Gold, 1991). Here we describe experiments designed to analyze the nature of the extracted features, and their relevance to the theory and psychophysics of object recognition. 1 Introduction Results of recent computational studies of visual recognition (e.g., Poggio and Edelman, 1990) indicate that the problem of recognition of 3D objects can be effectively reformulated in terms of standard pattern classification theory. According to this approach, an object is represented by a few of its 2D views, encoded as clusters in multidimentional space. Recognition of a novel view is then carried out by interpo- lating among the stored ...