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

Path similarity skeleton graph matching.

Xiang Bai1, Longin Jan Latecki

  • 1Department of electronics and Information Enginering, Huazhong University of Science and Technology, Wuhan, Hubei, PR China. xiang.bai@gmail.com

IEEE Transactions on Pattern Analysis and Machine Intelligence
|June 14, 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

Training-Free Ultra Small Model for Universal Sparse Reconstruction in Compressed Sensing.

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

OmniParser V2: Structured-Points-of-Thought for Unified Visual Text Parsing and Its Generality to Multimodal Large Language Models.

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

Dominant Direct Mechanism at Low Collision Energy Induced by the Nucleophile.

The journal of physical chemistry. A·2026
Same author

A fine-grained fundus image dataset for cataract severity assessment and diagnosis.

Scientific data·2026
Same author

Non-Iridium-Based Electrocatalysts for the Acidic Oxygen Evolution Reaction: Progress and Perspectives.

ACS applied materials & interfaces·2026
Same author

Self-Supervised Learning of Deep Embeddings for Classification and Identification of Dental Implants.

Journal of imaging·2026
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 shape recognition framework using object silhouettes and skeleton graphs. By comparing shortest paths between skeleton endpoints, it achieves accurate shape matching even with differing graph structures.

Area of Science:

  • Computer Vision
  • Pattern Recognition
  • Image Analysis

Background:

  • Object shape recognition is crucial in computer vision.
  • Traditional methods often struggle with variations in topology.
  • Skeleton graphs are useful representations but sensitive to structural changes.

Purpose of the Study:

  • To develop a novel framework for shape recognition.
  • To improve robustness against topological variations in skeleton graphs.
  • To enable accurate shape matching based on object silhouettes.

Main Methods:

  • Utilizing object silhouettes for shape representation.
  • Generating skeleton graphs from object contours.
  • Employing Discrete Curve Evolution for skeleton pruning.

Related Experiment Videos

  • Comparing shortest paths between skeleton endpoints for matching, ignoring overall graph topology.

    • Main Results:

    • The proposed method successfully matches visually similar skeleton graphs despite topological differences.
    • Accurate shape recognition is achieved even with articulations, stretching, and partial occlusion.
    • The approach demonstrates robustness in challenging real-world scenarios.

    Conclusions:

    • Comparing shortest paths between skeleton endpoints offers a powerful alternative to traditional graph matching.
    • This novel framework enhances the reliability of shape recognition systems.
    • The method shows significant potential for applications requiring robust object identification.