基于改进遗传算法的小波去噪的阈值优化  

Threshhold optimization for wavelet denosing based on improved genetic algorithm

作　　者：王志明[1] 伍朝华[1] 

机构地区：[1]湖南农业大学理学院,湖南长沙410128

出　　处：《计算机工程与设计》2008年第9期2381-2383,共3页Computer Engineering and Design

基　　金：湖南农业大学青年基金项目(06QN07)

摘　　要：根据基因重组原理,定义了新的反向逻辑交叉算子和随机逻辑交叉算子对标准遗传算法进行改进。利用改进的遗传算法求解多尺度小波分解每层系数的最优阈值,通过软阈值法对小波系数处理后进行小波重构。实验结果表明,利用改进的遗传算法进行小波去噪是可行的,且能够达到较高的信噪比。Classical genetic algorithm is improved based on pinciple ofgene reconfiguration. Reverse and random logical erossover operator are defined and used to implement gene reconfiguration. Then based on improved GA, every scale best thresholds are solved after decomposed by multiscale wavelet transform. Reconstructed signal is obtained by using the inverse wavelet transform after all coefficients are dealt with soft threshold method. Experimental results show that the method is effective and can obtain optimal signal-to-noise ration.

关 键 词：图像去噪 改进遗传算法 小波变换 阈值 逻辑交叉算子 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]