一种基于K-均值聚类优化的快速分形图像压缩算法  

A Fast Fractal Image Compression Algorithm Based on K-mean Clustering Optimization

作　　者：姜政[1] 江铭炎[1] 

机构地区：[1]山东大学信息科学与工程学院,山东济南250100

出　　处：《电气电子教学学报》2006年第2期44-46,60,共4页Journal of Electrical and Electronic Education

摘　　要：提出了一种基于K-均值聚类的快速分形图像压缩算法,对搜索窗中的父块和子块,根据其方差的不同,用K-均值聚类方法分别对子块和父块进行聚类,子块只对同一类中的父块进行匹配,从而大大缩短了编码时间。实验结果表明,与经典分形压缩算法相比,本文算法编码速度可提高5倍;同基于方差的快速分形压缩算法相比,本文算法也有明显的优势。In this paper, an accelerating algorithm based on K-mean clustering is proposed for fractal image encoding. Range and domain blocks are clustered by using K-mean clustering method, and range blocks search domain blocks in the same category, which can shorten encoding time significantly. The encoding speed of our method is 5 times faster than that of the classical Jacquin＇s algorithm. We also teste some other fast encoding schemes based on variance, and the experiment results show that our algorithms are superior to them.

关 键 词：K-均值聚类 分形块编码 图像压缩 

分 类 号：TN911.73[电子电信—通信与信息系统]