一种基于均匀颜色空间的色彩量化聚类算法  

A clustering algorithm for color images quantization in a homogeneous color space

作　　者：林洁[1] 余江[1] 陈天云[1] 

机构地区：[1]云南大学信息学院,云南昆明650091

出　　处：《云南大学学报（自然科学版）》2007年第S1期76-79,共4页Journal of Yunnan University(Natural Sciences Edition)

基　　金：云南省自然科学基金资助项目(2004F0010M)

摘　　要：主要研究了将彩色图像重新量化为仅有几种颜色的色彩量化问题.将RGB非均匀颜色空间变换到CIE1976L*a*b*均匀颜色空间,并根据图像在L*a*b*颜色空间中的a*,b*取值范围来自动选取最初始的聚类中心,再通过K均值动态聚类算法和最近临准则得到最终的量化结果.实验结果表明,算法具有一定的实用性,量化效果也较为理想.Some color quantization problems concerning re-quantization of a color image into a few numbers of colors are discussed.According to the value ranges of the color image's a*,b*,the firstly initial representative-points of the categories are automatically chosen in the homo-geneous color space of L*a*b*,which is transformed from the nonhomogeneous color space of RGB.Then,through the K-mean adaptive clustering and min-distances shortcut criterion the ultimate effects can be obtained.Experimental results show that this method is useful and the quantized effects can be accepted.

关 键 词：颜色空间 色彩量化 聚类分析 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]