Presentation + Paper
12 March 2024 Deep-learning-guided independent component analysis for characterizing facial skin melanin and hemoglobin distribution
Author Affiliations +
Abstract
One common approach to separatingmelanin and hemoglobin distribution from a color image is Independent Component Analysis (ICA). In this study, we propose a method based on deep learning to automatically detect suitable areas for successful facial pigmentation analysis. To do that, three deep learning models are utilized for segmentation and localization to offer a candidate region for ICA. The experiment was conducted using cross-polarized facial images selected from 200 subjects, and results showed that the deep learning-guided ICA can effectively identify regions of hyperpigmentation and successfully separate melanin and hemoglobin maps for evaluation.
Conference Presentation
© (2024) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Huisu Yoon, Geunho Jung, Semin Kim, Chanhyeok Lee, Sangwook Yoo, and Jongha Lee "Deep-learning-guided independent component analysis for characterizing facial skin melanin and hemoglobin distribution", Proc. SPIE 12845, Polarized Light and Optical Angular Momentum for Biomedical Diagnostics 2024, 1284504 (12 March 2024); https://doi.org/10.1117/12.3002337
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Skin

Independent component analysis

Image segmentation

Deep learning

Principal component analysis

Pigments

Back to Top