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

Computing texture boundaries from images.

H Voorhees1, T Poggio

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

Nature
|May 26, 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

Six ways to put the public at the heart of science and policy.

Nature·2026
Same journal

The complex truth about trust in science.

Nature·2026
Same journal

Have people stopped trusting science? The data tell a surprising story.

Nature·2026
Same journal

How FAIR data are helping to build trust in science.

Nature·2026
Same journal

Scientists should recognize their own political biases to build public trust.

Nature·2026
Same journal

Harmonizing standards and resources for the medical genome.

Nature·2026
See all related articles

This study presents a new algorithm for detecting texture boundaries in natural images. It proposes using blobs as texture elements and a statistical method to find boundaries, improving upon previous theories.

Area of Science:

  • Computer Vision
  • Computational Neuroscience
  • Image Processing

Background:

  • Current theories of texture vision focus on 'textons' (first-order differences in attributes like density, orientation, size, or contrast).
  • Psychological theories often use synthetic images, neglecting computation from natural grey-level images and boundary detection methods.
  • Previous hypotheses about textons, such as line segment crossings, are questioned by psychophysical findings.

Purpose of the Study:

  • To develop an algorithm for computing texture elements ('textons') from natural grey-level images.
  • To devise a method for accurately detecting texture boundaries in natural scenes.
  • To reconcile computational approaches with psychophysical observations in texture vision.

Main Methods:

Related Experiment Videos

  • Proposed using blobs, computed via a centre-surround operator, as texture elements.
  • Developed a non-parametric statistical method to compare local distributions of blob attributes.
  • Implemented and tested an algorithm for texture boundary detection on natural images.

    • Main Results:

    • The algorithm successfully detects texture boundaries in natural images.
    • The proposed method identifies blobs as effective texture elements.
    • The computational approach aligns with certain psychophysical findings, challenging prior texton hypotheses.

    Conclusions:

    • Blobs computed by centre-surround operators are viable texture elements for natural images.
    • A simple non-parametric statistic effectively locates texture boundaries by analyzing local blob attribute distributions.
    • The developed algorithm provides a practical method for texture boundary detection in real-world imagery.