高级搜索

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

基于图像局部曲面可展化的混合噪声抑制算法

王满利 马凤颖 张长森

王满利, 马凤颖, 张长森. 基于图像局部曲面可展化的混合噪声抑制算法[J]. 电子与信息学报, 2021, 43(11): 3291-3300. doi: 10.11999/JEIT201096
引用本文: 王满利, 马凤颖, 张长森. 基于图像局部曲面可展化的混合噪声抑制算法[J]. 电子与信息学报, 2021, 43(11): 3291-3300. doi: 10.11999/JEIT201096
Manli WANG, Fengying MA, Changsen ZHANG. Mixed Noise Suppression Algorithm Based on Developable Local Surface of Image[J]. Journal of Electronics & Information Technology, 2021, 43(11): 3291-3300. doi: 10.11999/JEIT201096
Citation: Manli WANG, Fengying MA, Changsen ZHANG. Mixed Noise Suppression Algorithm Based on Developable Local Surface of Image[J]. Journal of Electronics & Information Technology, 2021, 43(11): 3291-3300. doi: 10.11999/JEIT201096

基于图像局部曲面可展化的混合噪声抑制算法

doi: 10.11999/JEIT201096
基金项目: 国家自然科学基金(52074305),河南省科技攻关(212102210005),河南理工大学光电传感与智能测控河南省工程实验室开放基金(HELPSIMC-2020-00X)
详细信息
    作者简介:

    王满利:男,1981年生,博士,研究方向为信息与通信工程

    马凤颖:女,1994年生,硕士生,研究方向为现代通信技术

    张长森:男,1969年生,教授,研究方向为现代通信技术

    通讯作者:

    马凤颖 15139168603@163.com

  • 中图分类号: TN911.73; TP391.41

Mixed Noise Suppression Algorithm Based on Developable Local Surface of Image

Funds: The National Natural Science Foundation of China (52074305), The Science and Technology Research in Henan Province (212102210005), The Henan Polytechnic University Photoelectric Sensing and Intelligent Measurement and Control Provincial Program Laboratory Open Fund (HELPSIMC-2020-00X)
  • 摘要: 为满足基于旋翼无人机(UAV)载具的室外目标检测所需的低资源开销混合噪声抑制,该文提出一种基于图像局部曲面可展化的混合噪声抑制算法(DLS),该算法实现了局部曲面可展化算法和分层降噪算法优势互补,达到了两算法各自无法企及的降噪效果。首先,对图像进行局部可展化处理,抑制图像的椒盐噪声和低密度高斯噪声,得到初步降噪图像;接着,在空间域和傅里叶域分层降噪,在去除高斯噪声残余的同时,最大限度地保留图像边缘、纹理等细节;最后,迭代局部曲面可展化和分层降噪,进一步去除混合噪声残余成分,达到抑制目标检测图像混合噪声的目的。实验结果表明,在去除图像混合噪声时,相比于其他7种降噪算法,本文算法具有一定的优势,其降噪图像的主观视觉指标和客观数据指标统计优于其他7种算法。
  • 图  1  局部曲面可展化的直方图对比

    图  2  基于图像局部曲面可展化的混合噪声抑制模型框架

    图  3  局部曲面可展化降噪结果

    图  4  基于图像局部曲面可展化的混合噪声抑制算法实现流程图

    图  5  DLS算法降噪视觉效果图

    图  6  DLS算法对boat图片的降噪算法指标图

    图  7  局部方差

    图  8  LI1-LI2降噪结果对比

    图  9  8种降噪算法的PSNR指标

    表  1  DLS算法在BSD68和Set12的数据集的综合性能

    数据集指标数据
    PSNRMSESSIM
    Set1229.814618.21880.8630
    BSD6828.935024.13470.8266
    下载: 导出CSV

    表  2  8种算法降噪图像的MSE统计

    GN+SPNDDIDBM3DGCFWJSRTFMSFFFDNet本文方法
    5+0.037.5810.279.5838.7513.338.3710.567.74
    10+0.0210.3413.1624.1137.8114.8417.0815.8111.38
    LI115+0.0522.8234.0843.3448.5717.9324.9538.5914.76
    20+0.0531.3134.5858.0952.4622.6731.3146.2318.80
    30+0.166.4563.8680.9978.5238.6443.3676.6227.33
    40+0.1588.5680.3593.71106.9563.6355.3688.5840.67
    5+0.0311.9913.4919.0353.0351.8028.1512.1925.69
    10+0.0223.2525.9733.9452.5652.1839.4224.4533.10
    LI215+0.0540.2947.3950.7958.3353.6349.0946.0141.83
    20+0.0552.7252.5563.7060.4756.5953.7955.6347.22
    30+0.184.1172.2983.0373.1568.9761.8675.9955.43
    40+0.15103.1776.7994.3685.1593.5469.1787.5260.42
    下载: 导出CSV

    表  3  8种算法降噪图像的SSIM统计

    GN+SPNDDIDBM3DGCFWJSRTFMSFFFDNet本文方法
    5+0.030.4480.4640.8500.7910.8600.8890.4620.894
    10+0.020.5490.5990.7280.7730.8490.8160.5760.874
    LI115+0.050.3190.3710.5440.7330.8270.7540.3450.851
    20+0.050.3280.4290.4460.6940.7960.7120.3430.823
    30+0.10.1910.2730.2800.5910.6940.6330.1910.757
    40+0.150.1350.1860.1870.4840.5610.5220.1340.650
    5+0.030.5970.6080.8820.5520.4950.8200.6250.843
    10+0.020.6560.6890.8140.5350.4890.7330.6850.800
    LI215+0.050.4210.4680.6760.5200.4770.6010.4640.701
    20+0.050.4340.4970.5840.4970.4590.5320.4530.651
    30+0.10.2430.3180.3940.4540.4160.4360.2820.528
    40+0.150.1730.2430.2730.4090.3630.3860.1970.456
    下载: 导出CSV
  • [1] 张强. 基于BM3D的彩色图像混合噪声滤波算法研究[D]. [硕士论文], 吉林大学, 2019.

    ZHANG Qiang. Mixed noise filtering algorithm for color images based on BM3D[D]. [Master dissertation], Jilin University, 2019.
    [2] YIN Xiangrui, ZHAO Qianlong, LIU Jin, et al. Domain progressive 3D residual convolution network to improve low-dose CT imaging[J]. IEEE Transactions on Medical Imaging, 2019, 38(12): 2903–2913. doi: 10.1109/TMI.2019.2917258
    [3] LIU Jin, HU Yining, YANG Jian, et al. 3D feature constrained reconstruction for low-dose CT imaging[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2018, 28(5): 1232–1247. doi: 10.1109/TCSVT.2016.2643009
    [4] CHEN Yang, SHI Luyao, FENG Qianjing, et al. Artifact suppressed dictionary learning for low-dose CT image processing[J]. IEEE Transactions on Medical Imaging, 2014, 33(12): 2271–2292. doi: 10.1109/TMI.2014.2336860
    [5] FAN Haiyan, LI Chang, GUO Yulan, et al. Spatial–spectral total variation regularized low-rank tensor decomposition for hyperspectral image denoising[J]. IEEE Transactions on Geoscience and Remote Sensing, 2018, 56(10): 6196–6213. doi: 10.1109/TGRS.2018.2833473
    [6] ABAZARI R and LAKESTANI M. A hybrid denoising algorithm based on shearlet transform method and yaroslavsky’s filter[J]. Multimedia Tools and Applications, 2018, 77(14): 17829–17851. doi: 10.1007/s11042-018-5648-7
    [7] SHAHDOOSTI H R and KHAYAT O. Image denoising using sparse representation classification and non-subsampled shearlet transform[J]. Signal, Image and Video Processing, 2016, 10(6): 1081–1087. doi: 10.1007/s11760-016-0862-0
    [8] ZHANG Kai, ZUO Wangmeng, and ZHANG Lei. FFDNet: Toward a fast and flexible solution for CNN-based image denoising[J]. IEEE Transactions on Image Processing, 2018, 27(9): 4608–4622. doi: 10.1109/TIP.2018.2839891
    [9] ZHANG Jing, SANG Liu, WAN Zekang, et al. Deep convolutional neural network based on multi-scale feature extraction for image denoising[C]. The IEEE International Conference on Visual Communications and Image Processing (VCIP), Macau, China, 2020: 213–216. doi: 10.1109/VCIP49819.2020.9301843.
    [10] RAFIQUE H. Simulation of harmonic analysis, synthesis and Gibbs effect of periodic signals[C]. The 16th International Multi-Conference on Systems, Signals & Devices (SSD), Istanbul, Turkey, 2019: 282–287. doi: 10.1109/SSD.2019.8893281.
    [11] LI Wenhao, JIA Tong, CHEN Qiusheng, et al. Omnidirectional ring structured light noise filtering based on DCGAN network and autoencode[C]. The International Conference on Culture-oriented Science & Technology (ICCST), Beijing, China, 2020: 452–456. doi: 10.1109/ICCST50977.2020.00093.
    [12] GONG Yuanhao and SBALZARINI I F. Curvature filters efficiently reduce certain variational energies[J]. IEEE Transactions on Image Processing, 2017, 26(4): 1786–1798. doi: 10.1109/TIP.2017.2658954
    [13] 王满利, 田子建, 桂伟峰, 等. 基于高斯曲率优化和非下采样剪切波变换的高密度混合噪声去除算法[J]. 光子学报, 2019, 48(9): 0910003. doi: 10.3788/gzxb20194809.0910003

    WANG Manli, TIAN Zijian, GUI Weifeng, et al. High density mixed noise removal algorithm based on gaussian curvature optimization and non-subsampled shearlet transform[J]. Acta Photonica Sinica, 2019, 48(9): 0910003. doi: 10.3788/gzxb20194809.0910003
    [14] 王满利, 田子建, 张元刚. 曲率差分驱动的极小曲面滤波器[J]. 电子与信息学报, 2020, 42(3): 764–771. doi: 10.11999/JEIT190216

    WANG Manli, TIAN Zijian, and ZHANG Yuangang. Minimal surface filter driven by curvature difference[J]. Journal of Electronics &Information Technology, 2020, 42(3): 764–771. doi: 10.11999/JEIT190216
    [15] 汤成, 许建龙, 周志光. 改进的曲率滤波强噪声图像去噪方法[J]. 中国图象图形学报, 2019, 24(3): 346–356. doi: 10.11834/jig.180302

    TANG Cheng, XU Jianlong, and ZHOU Zhiguang. Strong noise image-denoising algorithm based on improved curvature filters[J]. Journal of Image and Graphics, 2019, 24(3): 346–356. doi: 10.11834/jig.180302
    [16] XU Zhiya, DAI Tao, NIU Li, et al. Sure-based dual domain image denoising[C]. The IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Calgary, Canada, 2018: 1418–1422. doi: 10.1109/ICASSP.2018.8461324.
    [17] KNAUS C and ZWICKER M. Dual-domain image denoising[C]. The IEEE International Conference on Image Processing, Melbourne, Australia, 2013: 440–444. doi: 10.1109/ICIP.2013.6738091.
    [18] DABOV K, FOI A, KATKOVNIK V, et al. Image denoising by sparse 3-D transform-domain collaborative filtering[J]. IEEE Transactions on Image Processing, 2007, 16(8): 2080–2095. doi: 10.1109/TIP.2007.901238
    [19] LIU Licheng, CHEN Long, CHEN C L P, et al. Weighted joint sparse representation for removing mixed noise in image[J]. IEEE Transactions on Cybernetics, 2017, 47(3): 600–611. doi: 10.1109/TCYB.2016.2521428
    [20] LIU Yinghui, GAO Kun, and NI Guoqiang. An improved trilateral filter for Gaussian and impulse noise removal[C]. The 2nd International Conference on Industrial Mechatronics and Automation, Wuhan, China, 2010: 385–388. doi: 10.1109/ICINDMA.2010.5538290.
  • 加载中
图(9) / 表(3)
计量
  • 文章访问数:  990
  • HTML全文浏览量:  546
  • PDF下载量:  92
  • 被引次数: 0
出版历程
  • 收稿日期:  2020-12-30
  • 修回日期:  2021-05-22
  • 网络出版日期:  2021-06-07
  • 刊出日期:  2021-11-23

目录

    /

    返回文章
    返回