Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

Shape classification using the inner-distance.

Haibin Ling¹, David W Jacobs

¹Department of Computer Science, University of Maryland, College Park 20742, USA. hbling@umiacs.umd.edu

IEEE Transactions on Pattern Analysis and Machine Intelligence

|December 16, 2006

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

GEOMETRY OF LONG-TAILED REPRESENTATION LEARNING: REBALANCING FEATURES FOR SKEWED DISTRIBUTIONS.

... International Conference on Learning Representations·2026

Same author

Setup-Independent Full Projector Compensation.

IEEE transactions on visualization and computer graphics·2026

Same author

DiffPC: Diffusion-Based Projector Photometric Compensation.

IEEE transactions on visualization and computer graphics·2026

Same author

Probing uric acid-related prognostic genes and their molecular mechanisms in prostate cancer based on transcriptomic data.

Discover oncology·2026

Same author

Allicin suppressed bladder cancer cell biological activities via regulation of the miR-26b-5p/PTEN axis in an <i>in vitro</i> study.

Archives of medical science : AMS·2026

Same author

Cortical layer multi-parameter analysis of neurovascular impairments in AD/ADRD rodent model with in vivo optical imaging.

Translational neurodegeneration·2025

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

We introduce inner-distance for shape analysis, offering robust descriptors for articulated objects. This method effectively captures part structure, outperforming traditional Euclidean distance in computer vision tasks.

Area of Science:

Computer Vision
Shape Analysis
Pattern Recognition

Background:

Part structure and articulation are critical in computer and human vision.
Existing shape descriptors struggle with articulated objects.

Purpose of the Study:

To develop articulation-robust shape descriptors using inner-distance.
To improve shape classification accuracy for complex and articulated shapes.

Main Methods:

Defining inner-distance as the shortest path length within a shape silhouette.
Developing three approaches: inner-distance with Multidimensional Scaling (MDS), inner-distance based shape contexts, and incorporating texture information.
Evaluating methods on diverse shape datasets including articulated objects, silhouettes, and motion data.

Related Experiment Videos

Main Results:

Inner-distance is insensitive to articulation and superior to Euclidean distance for capturing part structure.
Proposed methods demonstrate effective performance across various shape databases.
Texture information along shortest paths further enhances classification accuracy.

Conclusions:

Inner-distance is a valuable alternative to Euclidean distance for complex shape analysis.
The proposed inner-distance based descriptors offer improved robustness and accuracy for articulated shapes.
This approach advances shape recognition in computer vision applications.