基于预分类的非局部被动毫米波图像去噪算法  

Pre-Selection Based Non-Local Passive Millimeter Wave Image Denoising Algorithm

作　　者：余汪洋[1] 陈祥光[1] 吴磊[1] 

机构地区：[1]北京理工大学化工与环境学院,北京100081

出　　处：《北京理工大学学报》2015年第12期1303-1307,共5页Transactions of Beijing Institute of Technology

基　　金：中兵集团研究专项基金资助项目(20091041005)

摘　　要：针对被动毫米波图像的分辨率低,不具备丰富的纹理信息的特点,提出了一种基于预分类的非局部被动毫米波图像去噪算法(PBNL).利用图像梯度信息的奇异值分解获取图像的局部区域特征,根据不同的特征集将图像进行分类,并对不同的类别采取不同的去噪算法.实验结果表明,相对于非局部均值(NL-Means)算法,该方法在计算(时间)复杂度上有了明显的降低,降噪结果的PSNR值优于BM3D、各向异性去噪算法,并且在视觉上获得了更好的辨识效果.Given that the low resolution and poor texture information of passive millimeter wave images,apre-selection based image de-noising algorithm（PBNL）was proposed in this paper.The local regional characteristics of the image were obtained by using the singular value decomposition（SVD）of image gradient information,then the image was divided into different categories,and relevant algorithms were adopted.Experimental results show that,in contrast to the non local means（NL-Means）algorithm,the computational time complexity of the method proposed in this paper is significantly reduced and peak signal-to-noise ratio（PSNR）is superior to current state-of-art denoising algorithms,such as BM3 D,anisotropic denoising algorithm,and it can get a better recognition results visually.

关 键 词：被动毫米波 非局部均值 预分类 奇异值分解 

分 类 号：TN911.73[电子电信—通信与信息系统]