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

Skin segmentation using color pixel classification: analysis and comparison.

Son Lam Phung1, Abdesselam Bouzerdoum, Douglas Chai

  • 1School of Engineering and Mathematics, Edith Cowan University, WA 6027, Australia. s.phung@ieee.org

IEEE Transactions on Pattern Analysis and Machine Intelligence
|January 5, 2005
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

Single-molecule dynamics of fibrinogen and bovine serum albumin adsorption on silica nanoparticle coatings observed using high-speed atomic force microscopy.

Biointerphases·2025
Same author

Application of Event Cameras and Neuromorphic Computing to VSLAM: A Survey.

Biomimetics (Basel, Switzerland)·2024
Same author

RGB-D Data-Based Action Recognition: A Review.

Sensors (Basel, Switzerland)·2021
Same author

Correcting Susceptibility Artifacts of MRI Sensors in Brain Scanning: A 3D Anatomy-Guided Deep Learning Approach.

Sensors (Basel, Switzerland)·2021
Same author

Unbalanced Hybrid AOA/RSSI Localization for Simplified Wireless Sensor Networks.

Sensors (Basel, Switzerland)·2020
Same author

An unsupervised deep learning technique for susceptibility artifact correction in reversed phase-encoding EPI images.

Magnetic resonance imaging·2020

Skin segmentation using color pixel classification is robust across different color spaces. Optimal performance is achieved with the Bayesian or multilayer perceptron classifier, with minimal degradation from color quantization.

Area of Science:

  • Computer Vision
  • Image Processing
  • Pattern Recognition

Background:

  • Skin segmentation is crucial for various applications, including medical imaging and human-computer interaction.
  • Color pixel classification offers a promising approach for automated skin detection.

Purpose of the Study:

  • To investigate the impact of color representation, quantization, and classification algorithms on skin segmentation accuracy.
  • To identify optimal parameters for effective skin segmentation using color pixel classification.

Main Methods:

  • Evaluated multiple color spaces with a Bayesian classifier and histogram technique.
  • Assessed the effect of varying color quantization levels (bins per channel).
  • Compared the performance of Bayesian and multilayer perceptron classifiers against other algorithms.

Related Experiment Videos

Main Results:

  • Skin segmentation accuracy showed minimal dependence on the chosen color space.
  • Using only chrominance channels significantly degraded segmentation performance.
  • Color quantization down to 64 bins per channel yielded acceptable results, with higher bin counts improving performance.
  • Bayesian and multilayer perceptron classifiers outperformed other tested methods.

Conclusions:

  • Color pixel classification is a viable method for skin segmentation, largely independent of color space choice.
  • Careful selection of classification algorithms and consideration of quantization levels are important for optimizing performance.
  • Avoiding the use of chrominance channels alone is recommended for robust skin segmentation.