DMCA
A Model of Visual Recognition and Categorization (0)
| Citations: | 37 - 6 self |
BibTeX
@ARTICLE{Edelman_amodel,
author = {Shimon Edelman and Sharon Duvdevani-Bar},
title = {A Model of Visual Recognition and Categorization},
journal = {},
year = {},
volume = {352},
pages = {1191--1202}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
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 both of natural kinds and of 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...
Keyphrases
visual recognition visual system necessary computational substrate daily life situation artificial category require categorization representative combination several representative member natural kind target object open-ended character computer vision new instance stored view representational scheme categorization cannot
