三维块匹配波域调和滤波图像去噪  

Image Denoising by Mixing 3D Block Matching with Harmonic Filtering in Transform Domain

作　　者：吴静 周先春[1,2] 徐新菊 黄金 WU Jing;ZHOU Xian-chun;XU Xin-ju;HUANG Jin(School of Electronic and Information Engineering,Nanjing University of Information Science andTechnology,Nanjing 210044,China;Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology,NanjingUniversity of Information Science and Technology,Nanjing 210044,China)

机构地区：[1]南京信息工程大学电子与信息工程学院,南京210044 [2]南京信息工程大学江苏省大气环境与装备技术协同创新中心,南京210044

出　　处：《计算机科学》2020年第7期130-134,共5页Computer Science

基　　金：国家自然科学基金项目(11202106,61302188);江苏省“信息与通信工程”优势学科建设项目;江苏高校品牌专业建设工程资助项目。

摘　　要：针对当前图像去噪算法缺乏对整体结构的分析以及运算量过大的不足,提出了一种利用波域调和滤波扩散模型改进BM3D去噪技术的新算法。首先,利用传统的欧氏距离法将相似二维图像块合并,得到三维数组,再将联合滤波后的三维数组进行逆变换,得到图像的预估计数据。其次,通过小波分解变换提取预估计图像中的高频部分进行滤波,为避免边缘模糊,引用拉普拉斯高斯算法构建新算子并将其代入扩散模型。最后,进行小波重构,以得到原始图像的最终逼近,从而均衡运算速度和去噪性能,保护图像完整的结构信息。实验结果表明,新算法的去噪性能优异,内部信息保护更具完整性,运算速度合理,有利于实际应用。Aiming at remedy the defeat that the current denoising algorithms lack of analyses of integral structure and excessive computational complexity,this paper proposes an improved denoising algorithm using the harmonic filtering diffusion model in wave-domain to amend BM3D technology.Firstly,the algorithm uses the Euclidean distance to merge similar 2-D image fragments thus obtaining 3-D date arrays.Then it is dealt by collaborative filtering,and the pre-estimation data of the image would be obtained by inverse 3-D transformation.Wavelet decomposition is used to extract high frequency part of pre-denoised image to filter.Lastly,wavelet reconstruction is conducted to estimate the original image,in order to avoid edge ambiguity.Laplacian of Gassian is used to construct a new operator into the diffusion model for filtering,so as to balance the operation speed and denoising performance,and protect the complete structure of the image information.The experimental results show that the new algorithm has perfect denoising performance,more integrity of internal information protection,and short running time,which is beneficial to practical applications.

关 键 词：图像去噪 三维块匹配 小波分解 拉普拉斯高斯算法 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]