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

Class-based feature matching across unrestricted transformations.

Evgeniy Bart1, Shimon Ullman

  • 1California Institute of Technology, Pasadena, CA 91125, USA. eugenenbart@gmail.com

IEEE Transactions on Pattern Analysis and Machine Intelligence
|July 12, 2008
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

Relation DETR+: Exploring Explicit Position Relation Prior for Dense Prediction.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

RBF++: Quantifying and Optimizing Reasoning Boundaries across Measurable and Unmeasurable Capabilities for Chain-of-Thought Reasoning.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

CAFE: Cross-View Adaptive Fusion and Cluster Center Enhancement for Robust Multi-View Clustering.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

DIVER: Reinforced Diffusion Breaks Imitation Bottlenecks in End-to-End Autonomous Driving.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Ethics-Aware Safe Reinforcement Learning for Rare-Event Risk Control in Interactive Urban Driving.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Learning Shape Anchors for Holistic Indoor Scene Understanding.

IEEE transactions on pattern analysis and machine intelligence·2026
See all related articles

This study introduces a new feature matching method for object recognition. It improves accuracy by leveraging shared object parts across different viewing conditions, enabling robust invariant recognition.

Area of Science:

  • Computer Vision
  • Machine Learning
  • Pattern Recognition

Background:

  • Class-based feature matching is crucial for object recognition.
  • Existing methods struggle with large changes in viewing conditions.
  • Invariance to viewing conditions remains a significant challenge.

Purpose of the Study:

  • To develop a novel method for class-based feature matching robust to significant changes in viewing conditions.
  • To improve the accuracy and reliability of feature correspondence identification.
  • To enable invariant object recognition using the proposed feature matching technique.

Main Methods:

  • A novel method based on the consistency of shared features across viewing conditions.
  • Identifying subsets of objects sharing a specific feature.

Related Experiment Videos

  • Utilizing the property that feature appearance transformation is primarily feature-dependent, not object-dependent.
  • Comparing feature appearances only in similar viewing conditions to ensure reliable correspondence.

    • Main Results:

    • The proposed scheme reliably identifies corresponding features based on consistency requirements.
    • Achieves a dense set of accurate correspondences.
    • Significantly improves matching accuracy compared to previous schemes.
    • Demonstrates successful application in invariant object recognition.

    Conclusions:

    • The novel method offers a robust solution for feature matching under varying viewing conditions.
    • The approach overcomes limitations of previous methods, including restrictions to planar objects or affine transformations.
    • The technique does not require pre-existing examples of correct matches, simplifying its application.