改进的小波与Bayes阈值估计图像降噪算法  

Improved wavelet and Bayes threshold estimation algorithm for image denoising

作　　者：黄喜淦 王科社[1] 吴雅朋 黄彦曌 段密克 HUANG Xigan;WANG Keshe;WU Yapeng;HUANG Yanzhao;DUAN Mike(Mechanical Electrical Engineering School, Beijing Information Science ＆ Technology University, Beijing 100192 ,China)

机构地区：[1]北京信息科技大学机电工程学院,北京100192

出　　处：《北京信息科技大学学报（自然科学版）》2018年第3期95-98,共4页Journal of Beijing Information Science and Technology University

摘　　要：针对传统小波与Bayes阈值估计算法存在的不足,将小波多层变换方法和Bayes阈值估计算法相结合,提出了基于小波与Bayes自适应阈值估计的一种新的图像降噪方法。该算法改进了小波系数并进行Bayes阈值估计算法的处理,重构了经过处理的小波系数。经过仿真实验验证,该方法相对于传统的小波与Bayes阈值估计图像降噪算法在图像峰值信噪比(PSNR)指标衡量上更加优良,达到了图像降噪的优化效果。To improve the traditional wavelet denoising and the Bayes threshold estimation algorithm,the wavelet multi-layer transform method and the Bayes threshold estimation algorithm are combined. A new image denoising method based on wavelet and Bayes adaptive threshold estimation is proposed. The algorithm improves the wavelet coefficients and performs the processing of the Bayes threshold estimation algorithm,and reconstructs the processed wavelet coefficients. The algorithm improves the wavelet detail coefficients and processes the Bayes threshold estimation algorithm. Finally, the processed wavelet coefficients are reconstructed to get the noise reduction image. The experimental results show that the method is superior to the traditional wavelet Bayes threshold estimation image denoising method in peak signal to noise ratio（ PSNR） of the image,and the image denoising is optimized.

关 键 词：小波变换 Bayes阈值估计 图像降噪 峰值信噪比 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]