Philosophical Transactions of the Royal Society B Biological Sciences · 1997 · 112 citations · 27 references
ComputingComputer ScienceVision ScienceComputer VisionVisual PerceptionVisual PsychophysicsNeural Basis Of PerceptionObject RecognitionPattern RecognitionPerceptual LearningRepresentation LearningVisual SystemCategorization ModelsComputational VisionObject CategorizationObject ClassificationObject Recognition Under Variable Viewing ConditionsPerceptual CategorizationVisual CategorizationVisual System Modeling
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.
27
Nearest neighbor pattern classification
Thomas M. Cover, Peter E. Hart · IEEE Transactions on Information Theory · 1967 · 16.1K citations
An Algorithm for Vector Quantizer Design
Y. Linde, A. Buzo, Robert M. Gray · IEEE Transactions on Communications · 1980 · 7.2K citations
Recognition-by-components: A theory of human image understanding.
Irving Biederman · Psychological Review · 1987 · 5.6K citations