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

Discriminative feature co-occurrence selection for object detection.

Takeshi Mita1, Toshimitsu Kaneko, Bjorn Stenger

  • 1Multimedia Laboratory, Corporate Research and Development Center, Toshiba Corporation, Kawasaki, Japan. takeshi.mita@toshiba.co.jp

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

EXPRESS: RAGE in neutrophils triggers cerebral vasospasm in the hyperacute phase after subarachnoid hemorrhage.

Journal of cerebral blood flow and metabolism : official journal of the International Society of Cerebral Blood Flow and Metabolism·2026
Same author

Endothelial IRE1 signaling maintains blood-brain barrier integrity and limits neuroinflammation after traumatic brain injury.

Cell death & disease·2026
Same author

Regional and cell type-specific activation of the unfolded protein response after kainate injection in mice.

Neurochemistry international·2025
Same author

Characteristics of hub regions in the superficial white matter.

Cerebral cortex (New York, N.Y. : 1991)·2025
Same author

Adipose-Derived Stem Cell Sheets Prepared with Ascorbate 2-Phosphate Enhance Nerve Regeneration in Rat Sciatic Nerve Autografts.

Journal of reconstructive microsurgery·2025
Same author

Impact of ATF6 deletion on the embryonic brain development.

iScience·2025
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 a new object detection framework using feature co-occurrence for improved accuracy. The method enhances detection rates for objects like faces and hand gestures compared to existing techniques.

Area of Science:

  • Computer Vision
  • Machine Learning
  • Pattern Recognition

Background:

  • Object detection is crucial for many AI applications.
  • Existing methods like Viola-Jones utilize single features per classifier.
  • Limitations exist in capturing complex object structures with single features.

Purpose of the Study:

  • To develop an object detection framework leveraging discriminative feature co-occurrence.
  • To improve detection performance by considering relationships between multiple features.
  • To generalize and enhance the Viola-Jones framework.

Main Methods:

  • Utilized Sequential Forward Selection to identify feature co-occurrences during boosting.
  • Developed weak classifiers based on selected feature co-occurrences.

Related Experiment Videos

  • Generalized the Viola-Jones framework to incorporate multiple features per classifier.

    • Main Results:

    • The proposed algorithm achieved higher detection rates for faces and hand gestures.
    • Consistently outperformed the Viola-Jones framework in detection accuracy.
    • Maintained performance using the same number of features as the baseline.

    Conclusions:

    • Feature co-occurrence learning significantly improves object detection performance.
    • The generalized framework offers a more robust approach to object recognition.
    • This method provides a powerful alternative for discriminative object detection.