Ieee Transactions on Pattern Analysis and Machine Intelligence 1 Image Denoising Using the Higher Order Singular Value Decomposition
Ieee Transactions on Pattern Analysis and Machine Intelligence 1 Image Denoising Using the Higher Order Singular Value Decomposition
复制标题
DOI：
--
复制
发表时间：
--
期刊：
影响因子：
--
通讯作者：
Ajit Rajwade;Anand Rangarajan;Arunava Banerjee
中科院分区：
文献类型：
--
作者：
Ajit Rajwade;Anand Rangarajan;Arunava Banerjee
—在本文中，我们提出了一种非常简单而优雅的、基于补丁的机器学习技术，使用高阶奇异值分解（HOSVD）进行图像去噪。该技术简单地将来自噪声图像的相似补丁（具有由统计动机标准定义的相似性）分组到 3D 堆栈中，计算该堆栈的 HOSVD 系数，通过硬阈值处理这些系数，反转 HOSVD 变换并对每个像素执行假设平均以生成最终的滤波图像。我们的技术以原则性的方式选择所有必需的参数，并将它们与噪声模型相关联。我们还讨论了采用 HOSVD 作为图像去噪的适当变换的动机。我们通过实验证明了该技术在灰度和彩色图像上的出色性能，我们的方法在后者上产生了最先进的结果，在中等高的噪声水平下优于其他彩色图像去噪算法。还提出了最佳补丁大小选择和残差图像（去噪后）噪声方差估计的标准。
—In this paper, we propose a very simple and elegant, patch-based, machine learning technique for image denoising using the higher order singular value decomposition (HOSVD). The technique simply groups together similar patches from a noisy image (with similarity defined by a statistically motivated criterion) into a 3D stack, computes the HOSVD coefficients of this stack, manipulates these coefficients by hard thresholding, inverts the HOSVD transform and performs hypotheses averaging at each pixel to produce the final filtered image. Our technique chooses all required parameters in a principled way, relating them to the noise model. We also discuss our motivation for adopting the HOSVD as an appropriate transform for image denoising. We experimentally demonstrate the excellent performance of the technique on grayscale as well as color images with our method producing state of the art results on the latter, outperforming other color image denoising algorithms at moderately high noise levels. A criterion for optimal patch-size selection and noise variance estimation from the residual images (after denoising), is also presented.