Parallel Integration of Vision Modules

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...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Science (American Association for the Advancement of Science) Ročník 242; číslo 4877; s. 436 - 440
Hlavní autoři: Poggio, T., Gamble, E. B., Little, J. J.
Médium: Journal Article
Jazyk:angličtina
Vydáno: Washington, DC The American Association for the Advancement of Science 21.10.1988
American Association for the Advancement of Science
Témata:
ISSN:0036-8075, 1095-9203
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí: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.
Bibliografie:SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 14
ObjectType-Article-2
content type line 23
ObjectType-Article-1
ObjectType-Feature-2
ISSN:0036-8075
1095-9203
DOI:10.1126/science.3175666