自适应遗传算法与分形图像压缩结合的新方法  

New Method of Fractal Image Compression Combined with Adaptive Genetic Algorithms

作　　者：张梁斌[1] 周必水[2] 奚李峰[1] 

机构地区：[1]浙江万里学院计算机与信息学院,浙江宁波315100 [2]杭州电子科技大学软件分院,浙江杭州310018

出　　处：《计算机应用研究》2006年第7期249-251,248,共4页Application Research of Computers

基　　金：国家自然科学基金资助项目(10301029)

摘　　要：基于分形和分块迭代函数系统的特点,提出了一种改进的求解全局最优自相似分块的自适应遗传算法。算法中对父块个体的搜索空间采用格雷编码方法;定义子块与父块的最小匹配误差为适应度函数;提出改进遗传算法的线性自适应交叉和变异概率;采取优秀保护策略进行选择。实验结果表明,该方法在同类图像保证解压质量和压缩比的同时能明显缩短压缩时间,有效提高搜索效率。Put forward the adaptive genetic algorithm proposed for obtainment of matching domain blocks of fractal partition based on fractal and the partition iterated function system, which coded the position of father block with gray code, defined fitness for minimum distance of the child block matching with father block, adjusted GA＇s controls parameters of across and variance probability adaptively,selected optimal protect policy. After analyzing the experiment results, we can draw a conclusion that this method can shorten compression time greatly and improve the efficiency of research, at the same time ,the compression ratio and quality of image after decompression are quaranteed with the same images.

关 键 词：分形图像压缩 遗传算法 迭代函数系统 格雷码 自适应 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]