分散图象压缩的遗传算法  

On the Performance of Fractal Compression with An Improved Genetic Algorithm

作　　者：吴更石[1] 梁德群[1] 田原[1] 

机构地区：[1]西安交通大学图象处理与识别研究所

出　　处：《信号处理》1998年第A12期46-51,45,共7页Journal of Signal Processing

摘　　要：基于分形和PIFS函数的特点，提出一种改进的遗传算法用于分形压缩分块的定义域匹配搜索算法。该方法克服了原来分形图象压缩中分类匹配算法固有的局部最优性和随机搜索的缺点，是一种具导引的全局优化的搜索算法。分析和实验表明，该方法的图象压缩比高，解码质量好，若应用遗传算法的并行性，其编码速度也得到提高。An improved Genetic Algorithm for seeking the matching domain blocks of the fractal partition in image compression is proposed, which is based on the characteristic of the partition iterated function system and fractal.The algorithm is robust searching and optimazation algorithm. It overcomes the limit of the local optimal and random seeking of the matching algorithm with cIustering. It is a directed global optimazation seeking method. It can be shown by theoretical analyse and experiment that the new method can get higher compression ratio and better image quality.Also because the GAs can compute parallelly, new method can dramatically cut down the time of encoding.

关 键 词：分形图象压缩 四叉树 遗传算法 图象编码 

分 类 号：TN919.8[电子电信—通信与信息系统]