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

Efficient shape matching using shape contexts.

Greg Mori1, Serge Belongie, Jitendra Malik

  • 1School of Computing Science, Simon Fraser University, Burnaby, BC, Canada. mori@cs.sfu.ca

IEEE Transactions on Pattern Analysis and Machine Intelligence
|November 16, 2005
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

NeuralFeels with neural fields: Visuotactile perception for in-hand manipulation.

Science robotics·2024
Same author

Ego4D: Around the World in 3,600 Hours of Egocentric Video.

IEEE transactions on pattern analysis and machine intelligence·2024
Same author

Real-world humanoid locomotion with reinforcement learning.

Science robotics·2024
Same author

Navigating to objects in the real world.

Science robotics·2023
Same author

Fine-Grained Image Analysis With Deep Learning: A Survey.

IEEE transactions on pattern analysis and machine intelligence·2021
Same author

Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges.

IEEE transactions on pattern analysis and machine intelligence·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

Shape contexts accelerate similarity searches for shapes. Two novel algorithms, representative shape contexts and shapemes, enable rapid shape retrieval using efficient shape context comparisons and vector quantization.

Area of Science:

  • Computer Vision
  • Computational Geometry
  • Machine Learning

Background:

  • Shape retrieval is crucial for various applications, including computer vision and pattern recognition.
  • Existing methods for shape similarity search can be computationally intensive.

Purpose of the Study:

  • To introduce efficient algorithms for rapid shape retrieval.
  • To demonstrate the effectiveness of shape contexts in pruning similarity searches.

Main Methods:

  • Developed two algorithms: representative shape contexts and shapemes.
  • Representative shape contexts utilize a small subset of shape contexts for comparison.
  • Shapemes employ vector quantization within the shape context space to identify prototypical shape elements.

Related Experiment Videos

Main Results:

  • Shape contexts significantly accelerate the process of finding similar shapes.
  • The proposed algorithms enable rapid and efficient shape retrieval.
  • Representative shape contexts and shapemes offer effective solutions for large-scale shape databases.

Conclusions:

  • Shape contexts are a powerful tool for optimizing shape similarity searches.
  • The presented algorithms provide a scalable approach to shape retrieval.
  • This work contributes to advancements in efficient shape analysis and recognition.