16 February 2017 Component analysis and synthesis of dark circles under the eyes using a spectral image
Author Affiliations +
This paper proposes to apply nonlinear estimation of chromophore concentrations: melanin, oxy-hemoglobin, deoxyhemoglobin and shading to the real hyperspectral image of skin. Skin reflectance is captured in the wavelengths between 400nm and 700nm by hyperspectral scanner. Five-band wavelengths data are selected from skin reflectance. By using the cubic function which obtained by Monte Carlo simulation of light transport in multi-layered tissue, chromophore concentrations and shading are determined by minimize residual sum of squares of reflectance. When dark circles are appeared under the eyes, the subject looks tired and older. Therefore, woman apply cosmetic cares to remove dark circles. It is not clear about the relationship between color and chromophores distribution in the dark circles. Here, we applied the separation method of the skin four components to hyperspectral image of dark circle, and the separated components are modulated and synthesized. The synthesized images are evaluated to know which components are contributed into the appearance of dark circles. Result of the evaluation shows that the cause of dark circles for the one subject was mainly melanin pigmentation.
© (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Rina Akaho, Rina Akaho, Misa Hirose, Misa Hirose, Nobutoshi Ojima, Nobutoshi Ojima, Takanori Igarashi, Takanori Igarashi, Norimichi Tsumura, Norimichi Tsumura, } "Component analysis and synthesis of dark circles under the eyes using a spectral image", Proc. SPIE 10068, Imaging, Manipulation, and Analysis of Biomolecules, Cells, and Tissues XV, 1006815 (16 February 2017); doi: 10.1117/12.2252343; https://doi.org/10.1117/12.2252343

Back to Top