以混合算法建立宽带多光谱色彩表示空间  

Modified Multi-spectral Space for Color Representation Based on Hybrid Algorithm

作　　者：孔令罔[1] 朱元泓[2] 李琼[3] 

机构地区：[1]华中科技大学计算机科学与技术学院 [2]深圳职业技术学院,深圳市西丽湖518055 [3]武汉工程大学电气信息学院,武汉市卓刀泉路366号430070

出　　处：《武汉大学学报（信息科学版）》2006年第9期788-791,798,共5页Geomatics and Information Science of Wuhan University

基　　金：国家自然科学基金资助项目(60177005)

摘　　要：对整个原始光谱集进行基于自组织映射的聚类分析,以集群内光谱的平均值分布代替该集群,从而实现在对光谱分布的尖峰值平滑的同时实现原始光谱集的第一次压缩,并对压缩后的光谱集进行主成分分析,以提取的光谱主成分分量作为基张成宽带多光谱空间。On the basis of the hybrid algorithm constructed by cluster analysis and principal component analysis a newer multi-spectral space for color representation is developed. When cluster analysis applied using self-organized mapping the spectral distributions in each cluster are substituted by the mean distribution of those in the corresponding cluster. Further, principal component analysis is implemented on the compressed spectra set. Using the eigen spectral distributions as base to spanning the wide-band multi-spectral space for color representation. Results of experiments show that this newer multi-spectral space can represent and recon- struct the spectral distribution of the original color in a high accuracy.

关 键 词：聚类分析 主成分分析 色彩表示 宽带多光谱空间 

分 类 号：O438[机械工程—光学工程] P228.1[理学—光学]