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...

Full description

Saved in:
Bibliographic Details
Published in:Science (American Association for the Advancement of Science) Vol. 242; no. 4877; pp. 436 - 440
Main Authors: Poggio, T., Gamble, E. B., Little, J. J.
Format: Journal Article
Language:English
Published: Washington, DC The American Association for the Advancement of Science 21.10.1988
American Association for the Advancement of Science
Subjects:
Algorithms
Artificial intelligence
Biological and medical sciences
Color Perception
Computer programming & languages
Computerized, statistical medical data processing and models in biomedicine
Depth Perception
Edge detection
Eyes & eyesight
General aspects. Methods
Humans
Medical sciences
Models, Biological
Models, Psychological
Motion Perception
Parallel processing
Psychology & psychologists
Reflectance
Research facilities
Sensory perception
Stereo
Surface properties
Surface texture
Vision research
Vision, Ocular
Visual Perception
Biomedical data processing
Image analysis
Vision
Computer
Algorithm
Artificial intelligence
Biomedical engineering
ISSN:0036-8075, 1095-9203
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
Bibliography: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