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.
Science Policy Alerts

Site Tools

  • AAAS
  • Subscribe
  • Feedback

Site Search

Search Advanced

Science 29 January 1988:
Vol. 239. no. 4839, pp. 482 - 485
DOI: 10.1126/science.3340834
Prev | Table of Contents | Next

Articles

Science, Vol 239, Issue 4839, 482-485
Copyright © 1988 by American Association for the Advancement of Science

articles

Synthesizing a color algorithm from examples

AC Hurlbert and TA Poggio

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

A lightness algorithm that separates surface reflectance from illumination in a Mondrian world is synthesized automatically from a set of examples, which consist of pairs of input (intensity signal) and desired output (surface reflectance) images. The algorithm, which resembles a new lightness algorithm recently proposed by Land, is approximately equivalent to filtering the image through a center-surround receptive field in individual chromatic channels. The synthesizing technique, optimal linear estimation, requires only one assumption, that the operator that transforms input into output is linear. This assumption is true for a certain class of early vision algorithms that may therefore be synthesized in a similar way from examples. Other methods of synthesizing algorithms from examples, or "learning," such as back-propagation, do not yield a significantly better lightness algorithm.


THIS ARTICLE HAS BEEN CITED BY OTHER ARTICLES:
Spatial and temporal properties of cone signals in alert macaque primary visual cortex..
B. R. Conway and M. S. Livingstone (2006)
J. Neurosci. 26, 10826-10846
   Abstract »    Full Text »    PDF »
Color Contrast in Macaque V1.
B. R. Conway, D. H. Hubel, and M. S. Livingstone (2002)
Cereb Cortex 12, 915-925
   Abstract »    Full Text »    PDF »
Computer vision.
Y Aloimonos and A Rosenfeld (1991)
Science 253, 1249-1254
   Abstract »    PDF »
Perspectives on cognitive neuroscience.
P. Churchland and T. Sejnowski (1988)
Science 242, 741-745
   Abstract »    PDF »
Computational neuroscience.
T. Sejnowski, C Koch, and P. Churchland (1988)
Science 241, 1299-1306
   Abstract »    PDF »


ADVERTISEMENT
Click Me!

To Advertise     Find Products

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