Skin pigmentation detection and assessment

• Main Author: Lu, Haisheng
• Other Authors: Alex Chichung KOT
• Format: Thesis-Master by Coursework
• Language: English
• Published: Nanyang Technological University 2021
• Subjects: Engineering::Electrical and electronic engineering::Electronic systems::Signal processing
• Online Access: https://hdl.handle.net/10356/151845
• Institution: Nanyang Technological University

This thesis presents a region-based pigmentation detection method. The key of this method is to use Independent Component Analysis (ICA) in color space to extract melanin and hemoglobin layers from one single RGB face skin image. Large region pigmentations and small region pigmentations are detected separately and reduce the influence of shading and reflection areas on the face images effectively. The proposed method can more accurately detect the pigmentations compared with most of the existing methods. Based on this convincing result, a uniform pigmentation severity index is proposed to assess the severity of the pigmentation on the face.