Fractal image encoding with flexible classification sets  

作　　者：Jianji Wang Xuguang Lan Yuehu Liu Nanning Zheng 

机构地区：[1]Institute of Artificial Intelligence and Robotics,Xi’an Jiaotong University

出　　处：《Chinese Science Bulletin》2014年第14期1597-1606,共10页

基　　金：supported by the National Basic Research Program of China(2010CB327902);the National Natural Science Foundation of China(61231018)

摘　　要：Fractal image compression(FIC)technology is an interesting attempt at structure similarity-based image compression.It has been widely applied in many fields such as image encryption,image retrieval,image sharpening,and pattern recognition.However,overlong encoding time is the main difficulty for the application of FIC.In this paper,a new FIC speedup algorithm is proposed with two steps.Firstly,the simplified statistical variable expressions can speed up encoding twice more than the baseline fractal compression(BFC)without loss of image quality corresponding to BFC.Secondly,based on the fact that the affine self-similarity is equivalent to the absolute value of Pearson’s correlation coefficient,a new block classification strategy with flexible classification sets is proposed to speed up encoding further.The experiment results and theoretical analysis show that the proposed scheme achieves high performance in both image quality preservation and encoding efficiency.Fractal image compression （FIC） technology is an interesting attempt at structure similarity-based image compression. It has been widely applied in many fields such as image encryption, image retrieval, image sharpening, and pattern recognition. However, overlong encod- ing time is the main difficulty for the application of FIC. In this paper, a new FIC speedup algorithm is proposed with two steps. Firstly, the simplified statistical variable expressions can speed up encoding twice more than the baseline fractal compression （BFC） without loss of image quality corresponding to BFC. Secondly, based on the fact that the affine self-similarity is equivalent to the absolute value of Pearson＇s correlation coefficient, a new block classification strategy with flexible classification sets is proposed to speed up encoding further. The experiment results and theoretical analysis show that the proposed scheme achieves high performance in both image quality preservation and encoding efficiency.

关 键 词：分形图像编码 分类策略 Pearson相关系数 设置 分形图像压缩 图像质量 变量表达式 FIC 

分 类 号：TN919.81[电子电信—通信与信息系统]