对于带噪声的周期性纹理图像,提出一种基于二维秩约束的混合正则化去噪方法。该方法结合了全变分去噪理论和方法，并且利用该类图像低块秩的特性，对图像进行了低块秩约束。通过和全变分去噪方法比较可知，对于周期性纹理图像，混合正则化方法能有效地分离出噪声，并且能让图像很好地保持边缘。即使非严格的周期性纹理，该方法依然有很好的去噪效果。
资源文件列表
New_regularization/barb.png , 232752
New_regularization/Breg_GS_Iter.asv , 2704
New_regularization/Breg_GS_Iter.m , 2704
New_regularization/Breg_GS_Iter1.asv , 2798
New_regularization/Breg_GS_Iter1.m , 2871
New_regularization/Breg_Var_Iter.asv , 37
New_regularization/Breg_Var_Iter.m , 79
New_regularization/inv_P.m , 928
New_regularization/lena.png , 223986
New_regularization/LowPatchRank_TV.asv , 2498
New_regularization/LowPatchRank_TV.m , 2504
New_regularization/normalization.m , 94
New_regularization/norm_two.m , 51
New_regularization/P_mapping.m , 696
New_regularization/rank.jpg , 19172
New_regularization/shrink.asv , 111
New_regularization/shrink.m , 330
New_regularization/svt.asv , 132
New_regularization/svt.m , 138
New_regularization/toys.bmp , 66614