插值分析在织物染色计算机配色中的应用研究  

Research on Application of Principal Component Analysis in Computer Color Matching for Textile Dyeing

作　　者：李敏[1] 张秉森[1] 武洋洋[1] 

机构地区：[1]青岛大学信息工程学院,山东青岛266071

出　　处：《青岛大学学报（工程技术版）》2013年第1期27-31,37,共6页Journal of Qingdao University(Engineering & Technology Edition)

基　　金：国家自然科学基金资助项目(60973158;60743004)

摘　　要：针对织物染色配色这一复杂的非线性求解问题,本文主要对实验数据进行相关性分析,初步确定了染料质量浓度d1,d2,d3与三刺激值C,M,Y的基本关系,并利用插值法分别对实验数据进行一维和二维插值,以获得更多的数据;同时,利用Matlab拟合工具箱以及多元非线性回归,求出染料的质量浓度和三刺激值C,M,Y的非线性方程,并利用牛顿迭代法求解非线性方程组,以获得染料的质量浓度。实验结果表明,该模型所求出的染料质量浓度与实际测量值非常逼近,误差的绝对值在0.05以内。该模型精度高,准确性较好,可以应用到实际染色配色中。Aiming at solving the complex nonlinear problem of fabric dyeing color matching, we mainly get the basic relationship between textile dye recipe d1, d2 , d3 and their three stimulus values. In order to get more data, one-dimensional and two-dimensional interpolations to the experimental data are done respectively. Next the nonlinear equation of textile dye recipe and three stimulus values C, M and Y is established by using Matlab fitting toolbox and multivariate nonlinear regression. Finally, the nonlinear equation is solved by Newton iterative method to get the textile dye recipe. The experiment results show that the textile dye recipe we get by the model is very close to the actual measured values and the absolute value of error is less than 0.05. The model has a high precision and a good accuracy and it can be applied to the actual color matching.

关 键 词：计算机配色 插值 曲线拟合 曲面拟合 多元非线性回归 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]