基于小波变换和ROF模型的图像去噪算法  

Image denoising algorithm based on wavelet transform and ROF model

作　　者：王利娜[1] 何文章[1] 李长领 梁婕[1] 

机构地区：[1]天津职业技术师范大学理学院,天津300222 [2]天津职业技术师范大学汽车与交通学院,天津300222

出　　处：《天津职业技术师范大学学报》2015年第2期39-42,共4页Journal of Tianjin University of Technology and Education

基　　金：天津市应用基础及前沿技术研究计划项目(12JCYBJC10600)

摘　　要：小波变换和ROF模型是常用的图像去噪方法。为了获取高质量图像,降低或消除噪声对图像的影响,提出了一种新的图像去噪算法。该方法对噪声图像进行小波分解,并对其高频部分进行阈值去噪,之后利用ROF和拉普拉斯算子结合的模型去噪,并进行小波重构,得到最终的去噪图像。实验结果表明,此算法的去噪效果比小波去噪或ROF去噪明显,能在有效抑制图像噪声的同时,更好地保持图像的边缘、纹理等特征,有效地提高了图像质量。Wavelet transform and ROF model are common methods for image denoising. In order to keep maximum image edge and other important information while suppressing the noise, a new denoising algorithm is proposed in this paper. Firstly, the noisy image is decomposed using wavelet transform, then each detail image is first denoised with threshold method. Secondly, they are denoised by the model combined with ROF and the laplacian operator. Finally the denoised image is obtained from wavelet reconfiguration. The experimental results show that the proposed algorithm performs better than traditional methods of eliminating noise, and maintain the edge texture characteristic of the image nicely.

关 键 词：图像去噪 小波变换 ROF模型 拉普拉斯算子 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]