Salt and Pepper Noise Removal Method Based on the Edge-Adaptive Total Variation Model

被引:6
作者
Jiang, Yunyun [1 ]
Wang, Hefei [1 ]
Cai, Yi [1 ]
Fu, Bo [1 ]
机构
[1] Liaoning Normal Univ, Sch Comp Sci & Informat Technol, Dalian, Peoples R China
关键词
salt and pepper noise; median filter; adaptive total variation; edge detection; image stitching;
D O I
10.3389/fams.2022.918357
中图分类号
O1 [数学];
学科分类号
0701 ; 070101 ;
摘要
The traditional median filter can handle the image salt and pepper noise better. However, when the noise intensity is large, it is often necessary to enlarge the filter window to ensure the denoising effect, but the enlarged window may also cause excessive smoothing of the image, loss of texture details, and blurred edges. In view of the strong edge preservation characteristics of variational model denoising, we propose a salt and pepper noise removal method based on the edge-adaptive total variational model. Firstly, the image is segmented into edge regions and non-edge regions by edge detection operators. Secondly, the salt and pepper noise of the image is processed using the median filter and adaptive total variation model, respectively. Lastly, the non-edge regions processed by the median filter and the edge regions processed by the adaptive total variation model are extracted for splicing. The experimental results show that the method cannot only effectively remove salt and pepper noise, but also effectively protect the main edge details of the image.
引用
收藏
页数:9
相关论文
共 25 条
[1]   Blind and Semi-Blind Deblurring of Natural Images [J].
Almeida, Mariana S. C. ;
Almeida, Luis B. .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2010, 19 (01) :36-52
[2]  
Bing S., 2003, THESIS U CALIFORNIA
[3]  
Bing Z., 2021, THESIS ANQING NORMAL
[4]   Spatially Adapted Total Variation Model to Remove Multiplicative Noise [J].
Chen, Dai-Qiang ;
Cheng, Li-Zhi .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2012, 21 (04) :1650-1662
[5]  
Deng ZD, 2018, THESIS HUNAN U
[6]  
Fu B., 2021, 2021 IEEE INT C MULT, DOI [10.1109/ICME51207.2021.9428158, DOI 10.1109/ICME51207.2021.9428158]
[7]  
Fu B., 2009, THESIS LIAONING NORM
[8]   A convolutional neural networks denoising approach for salt and pepper noise [J].
Fu, Bo ;
Zhao, Xiaoyang ;
Li, Yi ;
Wang, Xianghai ;
Ren, Yonggong .
MULTIMEDIA TOOLS AND APPLICATIONS, 2019, 78 (21) :30707-30721
[9]   Patch-based contour prior image denoising for salt and pepper noise [J].
Fu, Bo ;
Zhao, XiaoYang ;
Li, Yi ;
Wang, XiangHai .
MULTIMEDIA TOOLS AND APPLICATIONS, 2019, 78 (21) :30865-30875
[10]   A salt and pepper noise image denoising method based on the generative classification [J].
Fu, Bo ;
Zhao, Xiaoyang ;
Song, Chuanming ;
Li, Ximing ;
Wang, Xianghai .
MULTIMEDIA TOOLS AND APPLICATIONS, 2019, 78 (09) :12043-12053