基于多小波阈值收缩与子带增强的图像去噪  

Image denoising based on multiwavelet shrinkage and subband enhancement

作　　者：王欣[1] 王云霄[1] 于晓[2] 庞云阶[1] 

机构地区：[1]吉林大学计算机科学与技术学院,长春130012 [2]空军航空大学信息中心,长春130022

出　　处：《哈尔滨工业大学学报》2008年第1期152-154,共3页Journal of Harbin Institute of Technology

基　　金：教育部博士点基金资助项目(20010183)

摘　　要：为保证在图像去噪的同时,尽量保留图像的边缘特征,提出一种新的基于多小波阈值收缩与子带增强相结合的图像去噪方法.该方法以多小波变换为基础,将变换后的多小波系数分为噪声相关系数和边缘相关系数,对变换系数进行软阈值多小波收缩消去噪声相关系数;阈值收缩是非线性变换,对图像边缘有平滑作用,因此,该方法提出在阈值收缩后进行线性的子带增强,增强边缘相关系数.实验表明:与单一的阈值收缩方法相比,该去噪方法不仅保留了图像的边缘特征,而且提高了去噪图像的峰值信噪比,优于普通的阈值收缩方法.To maintain more edge information in the process of image denoising, a new image denoising method based on multiwavelet threshold shrinkage and subband enhancement is presented. Based on multiwavelet transform（MWT）, the MWT coefficients were divided into two categories, the coefficients associated with noise and the coefficients associated with edges. The coefficients associated with noise were reduced by soft threshold muhiwavelet shrinkage. But this procedure is a non-linearity transformation and causes the edge smoothness. So subband enhancement function was introduced to enhance the edge related coefficients. The experimental results show that the presented denoising method can retain as many as possible the important signal features and increase the PSNR. Thus performs better than commonly used threshold shrinkage method.

关 键 词：多小波变换 图像去噪 多小波收缩 子带增强 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]