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

Multiscale categorical object recognition using contour fragments.

Jamie Shotton1, Andrew Blake, Roberto Cipolla

  • 1Toshiba Corporate R&D Center, Kawasaki, Japan. jamie@shotton.org

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

From bench to byte: A UK perspective on data-driven cancer research.

European journal of cancer (Oxford, England : 1990)·2026
Same author

Education Research: "Simulation Sharing": Use of a Cardiac Arrest Management Course Developed for Medicine Residents Applied to Neurocritical Care Fellows.

Neurology. Education·2025
Same author

Tumour purity assessment with deep learning in colorectal cancer and impact on molecular analysis.

The Journal of pathology·2024
Same author

Prediction of total and regional body composition from 3D body shape.

NPJ digital medicine·2024
Same author

Near fatal case of mirvetuximab soravtansine-gynx induced interstitial lung disease and a review of the primary literature.

Gynecologic oncology reports·2024
Same author

Efficacy of endoscopic decompression surgery for treatment of lumbar spinal stenosis.

Interventional pain medicine·2024
Same journal

HardFlow: Hard-Constrained Sampling for Flow-Matching Models Via Trajectory Optimization.

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

Industrial Brain: Self-Evolving Neuro-Symbolic Autonomy with Causal Resilience for Cyber-Physical Systems.

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

Adaptive Hardness-Driven Dictionary Distillation for Incomplete Streaming View Clustering.

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

Mixture of Global and Local Experts with Diffusion Transformer for Controllable Face Generation.

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

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads.

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

Achieving Text-based Person Retrieval with Any Granularity.

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

This study introduces an automatic visual recognition system using contour features for object detection. The system achieves robust and competitive results across various object categories and scales.

Area of Science:

  • Computer Vision
  • Machine Learning
  • Pattern Recognition

Background:

  • Psychophysical studies demonstrate object recognition from contour fragments.
  • Existing methods often struggle with variations in pose, scale, and articulation.

Purpose of the Study:

  • To develop an automatic visual recognition system utilizing local contour features.
  • To achieve robust object localization in space and scale.

Main Methods:

  • A novel chamfer matching formulation to build a class-specific codebook of contour fragments.
  • Boosting for combining fragments into a cascaded sliding-window classifier.
  • Mean shift for selecting strong responses as final detections.

Main Results:

Related Experiment Videos

  • The system demonstrates robustness to within-class variation, pose changes, and articulation.
  • Iterative learning on training and test sets improves classifier performance.
  • Highly competitive results achieved over 17 challenging categories.

Conclusions:

  • Contour features are a powerful cue for multi-scale and multi-class visual object recognition.
  • The proposed system offers an effective approach for automatic visual recognition.