101. Speckle noise removal via nonlocal low-rank regularization
- Author
-
Yulian Wu
- Subjects
Mathematical optimization ,Rank (linear algebra) ,MathematicsofComputing_NUMERICALANALYSIS ,0211 other engineering and technologies ,Regular polygon ,Matrix norm ,Speckle noise ,Low-rank approximation ,Augmented lagrange multiplier ,02 engineering and technology ,Peak signal-to-noise ratio ,Regularization (mathematics) ,Signal Processing ,0202 electrical engineering, electronic engineering, information engineering ,Media Technology ,020201 artificial intelligence & image processing ,Computer Vision and Pattern Recognition ,Electrical and Electronic Engineering ,Algorithm ,021101 geological & geomatics engineering ,Mathematics - Abstract
A nonlocal low-rank regularization approach is proposed for speckle noise removal.A nonconvex surrogate functions for the rank is proposed.We have developed a fast implementation using augmented Lagrange multiplier method.We demonstrate the excellent performance of the technique from PSNR and SSIM. This paper presents a novel method for speckle noise removal. We propose a nonlocal low-rank regularization (NLR) approach toward exploiting structured sparsity and explore its application into speckle noise removal. A nonconvex surrogate functions for the rank instead of the convex nuclear norm is proposed. To further improve the computational efficiency of the proposed algorithm, we have developed a fast implementation using augmented Lagrange multiplier (ALM) method. We experimentally demonstrate the excellent performance of the technique, in terms of both Peak Signal to Noise Ratio (PSNR) and Structural Similarity (SSIM).
- Published
- 2016