A model of visual recognition and categorization

• Published in: Philosophical transactions of the Royal Society of London. Series B. Biological sciences Vol. 352; no. 1358; pp. 1191 - 1202
• Main Authors: Edelman, Shimon, Duvdevani-Bar, Sharon
• Format: Journal Article
• Language: English
• Published: England The Royal Society 29.08.1997
• Subjects: Animals; Cognition - physiology; Computer pattern recognition; Dimensionality; Form Perception - physiology; Geometric shapes; Geometry; Humans; Interpolation; Mathematical manifolds; Mental objects; Neural Networks (Computer); Object recognition; Pattern Recognition, Automated; Pattern Recognition, Visual - physiology; Perceptual localization; Primates; Visual system
• ISSN: 0962-8436; 1471-2970
• DOI: 10.1098/rstb.1997.0102

To recognize a previously seen object, the visual system must overcome the variability in the object's appearance caused by factors such as illumination and pose. Developments in computer vision suggest that it may be possible to counter the influence of these factors, by learning to interpolate between stored views of the target object, taken under representative combinations of viewing conditions. Daily life situations, however, typically require categorization, rather than recognition, of objects. Due to the open-ended character of both natural and artificial categories, categorization cannot rely on interpolation between stored examples. Nonetheless, knowledge of several representative members, or prototypes, of each of the categories of interest can still provide the necessary computational substrate for the categorization of new instances. The resulting representational scheme based on similarities to prototypes appears to be computationally viable, and is readily mapped onto the mechanisms of biological vision revealed by recent psychophysical and physiological studies.