Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Synthesizing a color algorithm from examples.

A C Hurlbert1, T A Poggio

  • 1Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge 02139.

Science (New York, N.Y.)
|January 29, 1988
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Scaling theorems for zero crossings.

IEEE transactions on pattern analysis and machine intelligence·2011
Same author

On edge detection.

IEEE transactions on pattern analysis and machine intelligence·2011
Same author

Neuromagnetic correlates of visual motion coherence.

The European journal of neuroscience·2005
Same author

Perception of three-dimensional shape influences colour perception through mutual illumination.

Nature·2000
Same author

Discrimination of cone contrast changes as evidence for colour constancy in cerebral achromatopsia.

Experimental brain research·1998
Same author

Motion edges and regions guide image segmentation by colour.

Proceedings. Biological sciences·1997
Same journal

A native sulfur deposit in Gale crater, Mars.

Science (New York, N.Y.)·2026
Same journal

Coordinated demise of harmful algal blooms.

Science (New York, N.Y.)·2026
Same journal

Genetic effects put into context.

Science (New York, N.Y.)·2026
Same journal

Bacteria share proteins to survive antibiotics.

Science (New York, N.Y.)·2026
Same journal

Impacts shaped Earth's first continents.

Science (New York, N.Y.)·2026
Same journal

Erratum for the Report "Covalently bonded single-molecule junctions with stable and reversible photoswitched conductivity" by C. Jia <i>et al</i>.

Science (New York, N.Y.)·2026
See all related articles

A novel lightness algorithm was synthesized from examples to separate surface reflectance from illumination. This method, using optimal linear estimation, closely mirrors Land's algorithm and performs comparably to other learning techniques.

Area of Science:

  • Computer Vision
  • Computational Neuroscience
  • Image Processing

Background:

  • Separating surface reflectance from illumination is a fundamental challenge in computer vision.
  • Existing lightness algorithms often rely on specific assumptions about visual input.
  • Synthesizing algorithms from examples offers a data-driven approach to visual perception problems.

Purpose of the Study:

  • To automatically synthesize a lightness algorithm capable of separating surface reflectance from illumination.
  • To investigate the efficacy of optimal linear estimation for algorithm synthesis in early vision.
  • To compare the synthesized algorithm with existing methods, including Land's algorithm and back-propagation.

Main Methods:

  • A Mondrian world model was used to generate example image pairs (intensity signal and surface reflectance).

Related Experiment Videos

  • Optimal linear estimation was employed as the synthesis technique, assuming a linear operator.
  • The synthesized algorithm was analyzed and compared to Land's algorithm and back-propagation.

    • Main Results:

    • A functional lightness algorithm was successfully synthesized from example image pairs.
    • The synthesized algorithm demonstrated approximate equivalence to filtering via center-surround receptive fields.
    • Optimal linear estimation proved effective, requiring only the linearity assumption for the transformation operator.

    Conclusions:

    • Optimal linear estimation is a viable method for synthesizing early vision algorithms, such as lightness algorithms, from examples.
    • The synthesized algorithm performs comparably to established methods like Land's algorithm.
    • Alternative learning methods like back-propagation did not yield significantly superior results for this specific task.