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

Robust histogram construction from color invariants for object recognition.

Theo Gevers1, Harro Stokman

  • 1Intelligent Sensory Information Systems, Department of Computer Science, Faculty of Science, University of Amsterdam, Kruislaan 403, 1098 SJ Amsterdam, The Netherlands. gevers@science.uva.nl

IEEE Transactions on Pattern Analysis and Machine Intelligence
|September 24, 2004
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

Deepfake perpetrator conversation for adults with sexual abuse-related posttraumatic stress disorder: intervention development and multiple baseline study protocol.

European journal of psychotraumatology·2026
Same author

Virtual rescripting after loss using deepfake technology in prolonged grief treatment: a study protocol for a multiple baseline design.

European journal of psychotraumatology·2026
Same author

Interactive Learning of Intrinsic and Extrinsic Properties for All-Day Semantic Segmentation.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2023
Same author

Geometric Back-Propagation in Morphological Neural Networks.

IEEE transactions on pattern analysis and machine intelligence·2023
Same author

Corrigendum: Initial development of perpetrator confrontation using deepfake technology in victims with sexual violence-related PTSD and moral injury.

Frontiers in psychiatry·2023
Same author

Initial development of perpetrator confrontation using deepfake technology in victims with sexual violence-related PTSD and moral injury.

Frontiers in psychiatry·2022

This study introduces a novel object recognition method using variable kernel density estimators to improve histogram stability against sensor noise. The approach enhances recognition accuracy by robustly handling unstable color invariant values.

Area of Science:

  • Computer Vision
  • Image Processing
  • Machine Learning

Background:

  • Object recognition commonly uses histograms of photometric color invariants.
  • Sensor noise significantly degrades the stability of color invariant values, impacting recognition.
  • Existing methods struggle with noise-induced instability in color invariant representations.

Purpose of the Study:

  • To develop a robust object recognition scheme resilient to sensor noise.
  • To improve histogram-based image matching by addressing unstable color invariant values.
  • To propose a principled method for variable kernel density estimation in noisy image data.

Main Methods:

  • Modeling sensor noise propagation through color invariant variables to quantify uncertainty.
  • Utilizing derived uncertainty to parameterize variable kernel density estimators for histogram construction.

Related Experiment Videos

  • Computing histograms with variable kernel density estimators to suppress noise effects.

    • Main Results:

    • Quantified uncertainty associated with each color invariant value due to sensor noise.
    • Developed a robust histogram construction method using variable kernel density estimation.
    • Empirically demonstrated superior performance of the proposed method over traditional histogram schemes.

    Conclusions:

    • The proposed variable kernel density estimation approach effectively enhances object recognition robustness against sensor noise.
    • This method provides a principled way to handle uncertainty in color invariants for improved image matching.
    • The technique offers a significant improvement for object recognition tasks in the presence of sensor noise.