Novel Hybrid Sparse and Low-Rank Representation With Auto-Weight Minimax Lγ Concave Penalty for Image Denoising

被引:1
|
作者
Li, Bo [1 ]
Lv, Junrui [2 ]
Luo, Xuegang [2 ]
机构
[1] Sichuan Tourism Univ, Sch Informat & Engn, Chengdu 610100, Peoples R China
[2] Panzhihua Univ, Sch Math & Comp Sci, Panzhihua 617000, Peoples R China
来源
IEEE ACCESS | 2024年 / 12卷
关键词
non-convex regularization; sparse and low-rank representation; minimax L gamma concave penalty; Image denoising; RESTORATION;
D O I
10.1109/ACCESS.2024.3442373
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Image denoising techniques often rely on convex relaxations, which can introduce bias into estimations. To address this, non-convex regularizers like weighted nuclear norm minimization and weighted Schatten p-norm minimization have been proposed. However, current implementations often rely on heuristic weight selection, neglecting the potential of automated strategies. This work introduces a novel non-convex, non-separable regularization term aimed at achieving a hybrid representation that leverages both low-rank (LR) and global sparse gradient (GS) structures. An iteratively auto-weighting Equivalent Minimax L gamma Concave penalty (EMLC) is proposed for non-convex relaxations. To enhance sparsity and improve low-rank estimation, the EMLC-LRGS-based image denoising model is presented. This model integrates global gradient sparsity and LR priors within a unified framework using the EMLC penalty. The formulation addresses limitations of convex relaxations by employing an equivalent representation of the weight minimax L gamma concave penalty as a combined global sparsity and local smoothness regularizer in the gradient domain. This aligns more closely with the data acquisition model and prior knowledge. To exploit the inherent low-rank structure of images, an equivalent representation of the weighted L gamma norm is employed as a low-rank regularization term applied to groups of similar image patches. Efficient model resolution is achieved through an adaptive alternating direction method of multipliers (ADMM) algorithm that dynamically tunes the weighted parameter while promoting sparsity and a low-rank representation. The effectiveness of this approach is demonstrated through comprehensive comparisons with state-of-the-art image denoising models, showcasing its superiority in image denoising tasks.
引用
收藏
页码:127916 / 127930
页数:15
相关论文
共 50 条
  • [1] Image Denoising Using Low-Rank Dictionary and Sparse Representation
    Li, Tao
    Wang, Weiwei
    Feng, Xiangchu
    Xu, Long
    2014 TENTH INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND SECURITY (CIS), 2014, : 228 - 232
  • [2] Local Low-Rank and Sparse Representation for Hyperspectral Image Denoising
    Ma, Guanqun
    Huang, Ting-Zhu
    Haung, Jie
    Zheng, Chao-Chao
    IEEE ACCESS, 2019, 7 : 79850 - 79865
  • [3] Hyperspectral Image Denoising via Sparse Representation and Low-Rank Constraint
    Zhao, Yong-Qiang
    Yang, Jingxiang
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2015, 53 (01): : 296 - 308
  • [4] Adaptive Boosting for Image Denoising: Beyond Low-Rank Representation and Sparse Coding
    Wang, Bo
    Lu, Tao
    Xiong, Zixiang
    2016 23RD INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2016, : 1400 - 1405
  • [5] Iteratively Reweighted Minimax-Concave Penalty Minimization for Accurate Low-rank Plus Sparse Matrix Decomposition
    Pokala, Praveen Kumar
    Hemadri, Raghu Vamshi
    Seelamantula, Chandra Sekhar
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2022, 44 (12) : 8992 - 9010
  • [6] DEEP SPARSE AND LOW-RANK PRIOR FOR HYPERSPECTRAL IMAGE DENOISING
    Nguyen, Han V.
    Ulfarsson, Magnus O.
    Sigurdsson, Jakob
    Sveinsson, Johannes R.
    2022 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2022), 2022, : 1217 - 1220
  • [7] Conformal and Low-Rank Sparse Representation for Image Restoration
    Li, Jianwei
    Chen, Xiaowu
    Zou, Dongqing
    Gao, Bo
    Teng, Wei
    2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2015, : 235 - 243
  • [8] Hyperspectral image denoising with superpixel segmentation and low-rank representation
    Fan, Fan
    Ma, Yong
    Li, Chang
    Mei, Xiaoguang
    Huang, Jun
    Ma, Jiayi
    INFORMATION SCIENCES, 2017, 397 : 48 - 68
  • [9] Improvement of Low-Rank Representation Denoising Model Based on Nonconvex Penalty Function
    Liu Chengshi
    Zhao Zhigang
    Li Qiang
    PROCEEDINGS OF THE 4TH INTERNATIONAL CONFERENCE ON COMMUNICATION AND INFORMATION PROCESSING (ICCIP 2018), 2018, : 299 - 304
  • [10] A Denoising Algorithm for CT Image Using Low-rank Sparse Coding
    Lei, Yang
    Xu, Dong
    Zhou, Zhengyang
    Wang, Tonghe
    Dong, Xue
    Liu, Tian
    Dhabaan, Anees
    Curran, Walter J.
    Yang, Xiaofeng
    MEDICAL IMAGING 2018: IMAGE PROCESSING, 2018, 10574