Publication Date:
1988-10-21
Description:
Computer algorithms have been developed for several early vision processes, such as edge detection, stereopsis, motion, texture, and color, that give separate cues to the distance from the viewer of three-dimensional surfaces, their shape, and their material properties. Not surprisingly, biological vision systems still greatly outperform computer vision programs. One of the keys to the reliability, flexibility, and robustness of biological vision systems is their ability to integrate several visual cues. A computational technique for integrating different visual cues has now been developed and implemented with encouraging results on a parallel supercomputer.〈br /〉〈span class="detail_caption"〉Notes: 〈/span〉Poggio, T -- Gamble, E B -- Little, J J -- New York, N.Y. -- Science. 1988 Oct 21;242(4877):436-40.〈br /〉〈span class="detail_caption"〉Author address: 〈/span〉Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge 02139.〈br /〉〈span class="detail_caption"〉Record origin:〈/span〉 〈a href="http://www.ncbi.nlm.nih.gov/pubmed/3175666" target="_blank"〉PubMed〈/a〉
Keywords:
Algorithms
;
Color Perception
;
Depth Perception
;
Humans
;
*Models, Biological
;
*Models, Psychological
;
Motion Perception
;
*Vision, Ocular
;
*Visual Perception
Print ISSN:
0036-8075
Electronic ISSN:
1095-9203
Topics:
Biology
,
Chemistry and Pharmacology
,
Computer Science
,
Medicine
,
Natural Sciences in General
,
Physics
Permalink
