Extraction and regulation method of melanin and hemoglobin concentration in human face skin image

Abstract

The invention discloses a human face skin image melanin and hemoglobin concentration extraction and control method. The method includes the following steps: acquiring a human face skin polarized lightRGB color image and dividing the image into a plurality of sub-image blocks; performing the main component analysis and independent component analysis on each sub-image block to obtain a mixed matrixset; designing a mixed matrix effectiveness determination constraint condition, filtering out an effective mixed matrix subset from the mixed matrix set, and performing statistical operation to obtain an optimal mixed matrix; designing a weight control factor of the optimal mixed matrix, and constructing a human face skin melanin or hemoglobin concentration distribution image with the adjustableconcentration and a comprehensive synthetic image. According to the invention, an independent component analysis algorithm is adopted, and the mixed matrix effectiveness determination constraint condition is designed, the technical problem that in the existing melanin and hemoglobin concentration extraction method, the concentration extraction result is unstable and the error is large due to the fact that the concentration extraction is interfered by the invalid mixed matrix is solved.

Description

technical field [0001] The invention belongs to the technical field of digital image processing, and more specifically relates to a method for extracting and regulating the concentration of melanin and hemoglobin in human face skin images based on independent component analysis. Background technique [0002] There are two main types of current skin texture and characteristic analysis methods: contact chemical reagent analysis methods; non-contact digital image analysis methods. The former directly analyzes the skin texture and characteristics from the perspective of ingredients, and usually can obtain very precise quantitative chemical indicators. However, due to its contact operation, it may bring potential harm to the subjects and may cause the subjects to resist. The latter, due to its non-contact characteristics, makes it easier for subjects to accept the analysis process, and has been accepted by more and more skin-related institutions, but the number of quantitative in...

AI Technical Summary

Problems solved by technology

Emphatically, in the present invention, according to the distribution characteristics of melanin and hemoglobin in the R / G / B three-color, the mixing matrix validity determination constraint conditions are designed, which realizes good filtering of the original mixing matrix set, and solves the problem of existing melanin In the hemoglobin concentration extraction method, due to the interference of the concentration extraction by the invalid mixing matrix, the concentration extraction result is unstable and the technical problem is large error

Images