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 Concept Videos

Pigmentation01:19

Pigmentation

2.4K
The color of the skin is influenced by a number of pigments, including melanin, carotene, and hemoglobin. Recall that melanin is produced by cells called melanocytes, which are found scattered throughout the stratum basale of the epidermis. The melanin is transferred to the keratinocytes via melanosomes.
Melanin occurs in two primary forms: eumelanin that provides black and brown pigment and pheomelanin that provides red color. Dark-skinned individuals produce more melanin than those with pale...
2.4K
Photoreceptors and Visual Pathways01:22

Photoreceptors and Visual Pathways

6.0K
At the molecular level, visual signals trigger transformations in photopigment molecules, resulting in changes in the photoreceptor cell's membrane potential. The photon's energy level is denoted by its wavelength, with each specific wavelength of visible light associated with a distinct color. The spectral range of visible light, classified as electromagnetic radiation, spans from 380 to 720 nm. Electromagnetic radiation wavelengths exceeding 720 nm fall under the infrared category,...
6.0K
Skin Cancer01:30

Skin Cancer

4.1K
Skin cancer is a type of cancer that occurs when there is an abnormal growth of skin cells, usually triggered by damage to the DNA within the skin cells. It is primarily caused by exposure to ultraviolet (UV) radiation from the sun or artificial sources like tanning beds. Skin cancer is the most common type of cancer worldwide, and its incidence continues to rise.
Basal Cell Carcinoma (BCC): BCC is the most common type of skin cancer, accounting for about 80% of cases. It typically develops in...
4.1K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Investigating the Design of a Photoplethysmography Device for Vital Sign Monitoring.

Sensors (Basel, Switzerland)·2025
Same author

Performance Evaluation of a Mesh-Topology LoRa Network.

Sensors (Basel, Switzerland)·2025
Same author

Predicting mitochondrial fission, fusion and depolarisation event locations from a single z-stack.

PloS one·2023
Same author

DRP1 mutations associated with EMPF1 encephalopathy alter mitochondrial membrane potential and metabolic programs.

Journal of cell science·2023
Same author

Canary in the coliform mine: Exploring the industrial application limits of a microbial respiration alarm system.

PloS one·2021
Same author

Mitochondrial event localiser (MEL) to quantitativelydescribe fission, fusion and depolarisation in the three-dimensional space.

PloS one·2020

Related Experiment Video

Updated: Jun 25, 2025

Precision Implementation of Minimal Erythema Dose MED Testing to Assess Individual Variation in Human Inflammatory Response
06:31

Precision Implementation of Minimal Erythema Dose MED Testing to Assess Individual Variation in Human Inflammatory Response

Published on: October 3, 2019

8.6K

Skin Tone Estimation under Diverse Lighting Conditions.

Success K Mbatha1, Marthinus J Booysen1,2, Rensu P Theart1

  • 1Department of E&E, Stellenbosch University, Stellenbosch 7602, South Africa.

Journal of Imaging
|May 24, 2024
PubMed
Summary

This study developed a convolutional neural network model to accurately estimate skin tone under varied lighting conditions. The model shows promise for improving fairness in computer vision applications across diverse skin pigmentation levels.

Keywords:
CNNMonk skin tonelighting conditionsmachine learningskin tone classificationskin tone estimation

More Related Videos

Measuring Spatially- and Directionally-varying Light Scattering from Biological Material
11:57

Measuring Spatially- and Directionally-varying Light Scattering from Biological Material

Published on: May 20, 2013

13.5K
Multimodal Imaging and Spectroscopy Fiber-bundle Microendoscopy Platform for Non-invasive, In Vivo Tissue Analysis
10:35

Multimodal Imaging and Spectroscopy Fiber-bundle Microendoscopy Platform for Non-invasive, In Vivo Tissue Analysis

Published on: October 17, 2016

7.9K

Related Experiment Videos

Last Updated: Jun 25, 2025

Precision Implementation of Minimal Erythema Dose MED Testing to Assess Individual Variation in Human Inflammatory Response
06:31

Precision Implementation of Minimal Erythema Dose MED Testing to Assess Individual Variation in Human Inflammatory Response

Published on: October 3, 2019

8.6K
Measuring Spatially- and Directionally-varying Light Scattering from Biological Material
11:57

Measuring Spatially- and Directionally-varying Light Scattering from Biological Material

Published on: May 20, 2013

13.5K
Multimodal Imaging and Spectroscopy Fiber-bundle Microendoscopy Platform for Non-invasive, In Vivo Tissue Analysis
10:35

Multimodal Imaging and Spectroscopy Fiber-bundle Microendoscopy Platform for Non-invasive, In Vivo Tissue Analysis

Published on: October 17, 2016

7.9K

Area of Science:

  • Computer Vision
  • Biomedical Engineering
  • Artificial Intelligence

Background:

  • Accurate skin tone estimation is crucial for fair and high-performing computer vision applications, including medical diagnosis and facial recognition.
  • Illumination significantly impacts perceived skin tone, posing challenges for consistent analysis across different lighting conditions.
  • Existing methods struggle with accuracy across the full spectrum of human skin pigmentation.

Purpose of the Study:

  • To refine and evaluate a convolutional neural network (CNN) model for robust skin tone estimation.
  • To ensure consistent accuracy of the model across diverse skin tones and various lighting scenarios.
  • To improve the fairness and reliability of computer vision systems utilizing skin tone data.

Main Methods:

  • A dataset of 21,375 images from volunteers representing the full skin pigmentation spectrum was collected.
  • A convolutional neural network (CNN) model was developed and assessed for skin tone estimation.
  • The Monk Skin Tone Scale (10-point) was utilized to categorize and evaluate skin tones.

Main Results:

  • A regression-based CNN model demonstrated superior performance with an estimated-to-target distance of 0.5.
  • An accuracy of 85.45% and 97.16% was achieved using a threshold of 2 for estimated-to-target skin tone distance.
  • The model showed strong accuracy for lighter skin tones, moderate for darker tones, and lower for middle tones.

Conclusions:

  • The developed CNN model provides a reliable method for estimating skin tone under varying illumination.
  • The model's performance highlights the potential to enhance fairness in computer vision applications.
  • Further research may focus on improving accuracy for middle-toned skin and expanding the application scope.