中医面诊中面部肤色特征基函数确定  

Complexion Basis Function Determine in TCM Facial Diagnosis

作　　者：王立娜[1] 蔡轶珩[1] 

机构地区：[1]北京工业大学电子信息与控制工程学院,北京100022

出　　处：《测控技术》2016年第2期129-133,共5页Measurement & Control Technology

基　　金：国家自然科学基金项目(61201360)

摘　　要：为满足中医面诊中对面色精确描述的要求,用光谱反射率来表述颜色。基于有限维模型,面部的光谱反射率可以用一组基函数的线性组合表示。因此可采用少量的图像通道数据求解像素位置基函数系数,复原面部各像素点的光谱反射率。而基函数的确定是光谱反射率复原的基础,针对面部肤色的特点,基于标准色系及真实肤色研究了不同面部光谱反射率样本集条件下,确定的面部光谱反射率基函数对复原精度的影响,并确定了适用于面部光谱反射率复原的优选样本集及基函数组合。结果表明,优选样本集使用较少的基函数就可以达到良好的复原效果,将为基于中医面诊光谱反射率复原提供依据,进而促进中医面诊的客观化发展。To meet the demand of complexion’ s accurate description in TCM facial diagnosis,the color needs to be expressed with spectral reflectance.Based on the finite dimension model,the facial spectral reflectance can be expressed as a linear combination with a set of basis functions.Therefore,a small amount of image channel data can be used to solve the basis function coefficients at the pixel,thus recovering the facial spectral reflectance of each pixel.The determination of basis functions is the basis of spectral reflectance recovery,based on the characteristics of facial skin color,the influence of facial spectral reflectance basis functions of fixed number on the accuracy recovery of spectral with different facial spectral reflectance sample set which is based on the standard color and true skin color is studied,the optimum sample set and the basis functions applying to facial spectral reflectance recovery are determined.The results show that the optimum sample set achieves better recovery results with fewer basis functions,the results will provide basis for the facial reflectance spectra recovcry,thus contribute to the development of TCM facial diagnosis objectification.

关 键 词：光谱反射率复原 有限维模型 基函数 中医面诊 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]