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

Parallel integration of vision modules.

T Poggio1, E B Gamble, J J Little

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

Science (New York, N.Y.)
|October 21, 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

Correction: Excess of NPM-ALK oncogenic signaling promotes cellular apoptosis and drug dependency.

Oncogene·2025
Same author

An analysis of training and generalization errors in shallow and deep networks.

Neural networks : the official journal of the International Neural Network Society·2019
Same author

Response from sinha and poggio.

Trends in cognitive sciences·2011
Same author

Multiclass cancer diagnosis using tumor gene expression signatures.

Proceedings of the National Academy of Sciences of the United States of America·2001
Same author

Learning in brains and machines.

Spatial vision·2001
Same author

Categorical representation of visual stimuli in the primate prefrontal cortex.

Science (New York, N.Y.)·2001
Same journal

Erratum for the Research Article "Detecting supramolecular organic nanoparticles during heat wave".

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

Local signals, systemic decline.

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

The mechanics of liver regeneration.

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

Computing in a memory with physics.

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

Retraction.

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

Making time.

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

Researchers developed a new computational technique to integrate visual cues, improving computer vision performance. This method enhances the ability of artificial systems to perceive 3D surfaces, mimicking biological vision systems.

Area of Science:

  • Computer Vision
  • Computational Neuroscience
  • Artificial Intelligence

Background:

  • Computer algorithms exist for early vision processes like edge detection, stereopsis, motion, texture, and color.
  • Biological vision systems outperform computer vision due to their ability to integrate multiple visual cues.
  • Current computer vision systems often process visual cues separately, limiting their robustness and flexibility.

Purpose of the Study:

  • To develop a novel computational technique for integrating diverse visual cues.
  • To enhance the performance and robustness of computer vision systems by mimicking biological integration strategies.
  • To implement and evaluate this integration technique on a parallel supercomputer.

Main Methods:

  • Development of a new computational algorithm designed for multi-cue integration in vision.

Related Experiment Videos

  • Implementation of the algorithm on a parallel supercomputing architecture.
  • Testing and evaluation of the integrated visual cue processing against established benchmarks.

    • Main Results:

    • The developed computational technique demonstrated encouraging results in integrating visual cues.
    • The integrated approach showed improvements in processing information about 3D surfaces, shape, and material properties.
    • Performance gains were observed, suggesting enhanced reliability and flexibility compared to separate cue processing.

    Conclusions:

    • Integrating multiple visual cues computationally is key to advancing computer vision capabilities.
    • The new technique shows promise for creating more robust and biologically plausible artificial vision systems.
    • Further development and application on parallel architectures can lead to significant breakthroughs in artificial perception.