Note to users. If you're seeing this message, it means that your browser cannot find this page's style/presentation instructions -- or possibly that you are using a browser that does not support current Web standards. Find out more about why this message is appearing, and what you can do to make your experience of our site the best it can be.

Site Tools

  • AAAS
  • Subscribe
  • Feedback

Site Search

Search Advanced

Science 21 October 1988:
Vol. 242. no. 4877, pp. 436 - 440
DOI: 10.1126/science.3175666
Prev | Table of Contents | Next

Articles

Science, Vol 242, Issue 4877, 436-440
Copyright © 1988 by American Association for the Advancement of Science

articles

Parallel integration of vision modules

T Poggio, EB Gamble, and JJ Little

Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge 02139.

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.


THIS ARTICLE HAS BEEN CITED BY OTHER ARTICLES:
Computer vision.
Y Aloimonos and A Rosenfeld (1991)
Science 253, 1249-1254
   Abstract »    PDF »
A two-dimensional analog VLSI circuit for detecting discontinuities in early vision.
J. Harris, C Koch, and J Luo (1990)
Science 248, 1209-1211
   Abstract »    PDF »
Seeing in Parallel: the Vision Machine.
J. J. Little, T. Poggio, and E. B. Gamble JR (1988)
International Journal of High Performance Computing Applications 2, 13-28
   Abstract »    PDF »


To Advertise     Find Products

Science. ISSN 0036-8075 (print), 1095-9203 (online)