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

Object recognition and segmentation by a fragment-based hierarchy.

Shimon Ullman1

  • 1Department of Computer Science and Applied Mathematics, The Weizmann Institute of Science, Rehovot 76100, Israel. shimon.ullman@weizmann.ac.il

Trends in Cognitive Sciences
|December 26, 2006
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

Neural correlates of minimal recognizable configurations in the human brain.

Cell reports·2025
Same author

Human-like scene interpretation by a guided counterstream processing.

Proceedings of the National Academy of Sciences of the United States of America·2023
Same author

Gaze following requires early visual experience.

Proceedings of the National Academy of Sciences of the United States of America·2022
Same author

Author Correction: View-tuned and view-invariant face encoding in IT cortex is explained by selected natural image fragments.

Scientific reports·2021
Same author

Oculo-retinal dynamics can explain the perception of minimal recognizable configurations.

Proceedings of the National Academy of Sciences of the United States of America·2021
Same author

View-tuned and view-invariant face encoding in IT cortex is explained by selected natural image fragments.

Scientific reports·2021
Same journal

Misinformation as strategy: Epistemic consequences and the undermining of shared truth.

Trends in cognitive sciences·2026
Same journal

Geographical psychology: Spatial variation in psychological phenomena and their consequences.

Trends in cognitive sciences·2026
Same journal

Multi-brain neurofeedback: what are we training for?

Trends in cognitive sciences·2026
Same journal

The developing vocal self.

Trends in cognitive sciences·2026
Same journal

Searching beyond decrements: Attentional guidance across the adult lifespan.

Trends in cognitive sciences·2026
Same journal

Looking into working memory through micro eye movements.

Trends in cognitive sciences·2026
See all related articles

This study introduces a novel computational approach for visual category learning and recognition. It uses a hierarchy of extracted fragments to identify objects, segment them in cluttered scenes, and understand object parts.

Area of Science:

  • Cognitive Science
  • Computer Vision
  • Neuroscience

Background:

  • The human brain efficiently learns visual categories from limited examples.
  • Understanding the computational mechanisms behind visual category learning is a key challenge.

Purpose of the Study:

  • To present a new computational framework for visual category learning and recognition.
  • To demonstrate how extracted object fragments can be used for multiple visual tasks.

Main Methods:

  • Objects are represented by a hierarchy of class-specific fragments extracted from observed examples.
  • These fragments are selected for their high informational content for categorization.
  • The fragment hierarchy is applied to general categorization, individual object recognition, and part identification.

Related Experiment Videos

Main Results:

  • The approach enables recognition by combining stored fragment hierarchies with object segmentation.
  • A top-down process delineates object boundaries in complex, cluttered scenes.
  • The method is computationally effective.

Conclusions:

  • This fragment-based hierarchy offers a potential framework for human visual categorization, recognition, and segmentation.
  • The approach integrates multiple visual processing tasks using a unified representation.
  • It provides insights into the computational strategies employed by the brain for visual perception.