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

快速自适应非局部空间加权与隶属度连接的模糊C-均值噪声图像分割算法

王小鹏 王庆圣 焦建军 梁金诚

王小鹏, 王庆圣, 焦建军, 梁金诚. 快速自适应非局部空间加权与隶属度连接的模糊C-均值噪声图像分割算法[J]. 电子与信息学报, 2021, 43(1): 171-178. doi: 10.11999/JEIT191016
引用本文: 王小鹏, 王庆圣, 焦建军, 梁金诚. 快速自适应非局部空间加权与隶属度连接的模糊C-均值噪声图像分割算法[J]. 电子与信息学报, 2021, 43(1): 171-178. doi: 10.11999/JEIT191016
Xiaopeng WANG, Qingsheng WANG, Jianjun JIAO, Jincheng LIANG. Fuzzy C-Means Clustering with Fast and Adaptive Non-local Spatial Constraint and Membership Linking for Noise Image Segmentation[J]. Journal of Electronics & Information Technology, 2021, 43(1): 171-178. doi: 10.11999/JEIT191016
Citation: Xiaopeng WANG, Qingsheng WANG, Jianjun JIAO, Jincheng LIANG. Fuzzy C-Means Clustering with Fast and Adaptive Non-local Spatial Constraint and Membership Linking for Noise Image Segmentation[J]. Journal of Electronics & Information Technology, 2021, 43(1): 171-178. doi: 10.11999/JEIT191016

快速自适应非局部空间加权与隶属度连接的模糊C-均值噪声图像分割算法

doi: 10.11999/JEIT191016
基金项目: 国家自然科学基金(61761027)
详细信息
    作者简介:

    王小鹏:男,1969年生,博士,教授,研究方向为图像分析,信号与信息处理

    王庆圣:男,1995年生,硕士生,研究方向为图像处理与模式识别

    焦建军:男,1984年生,博士生,研究方向为图像分析

    梁金诚:男,1997年生,硕士生,研究方向为图像处理与目标检测

    通讯作者:

    王小鹏 wangxp1969@sina.com

  • 中图分类号: TN911.73; TP391.4

Fuzzy C-Means Clustering with Fast and Adaptive Non-local Spatial Constraint and Membership Linking for Noise Image Segmentation

Funds: The National Natural Science Foundation of China (61761027)
  • 摘要:

    针对传统模糊C-均值聚类(FCM)算法难以对噪声图像进行分割的问题,该文提出一种快速自适应非局部空间加权与隶属度连接的模糊FCM抗噪图像分割算法。首先,利用一种非局部空间信息快速计算方法,将以图像所有像素为循环的原始非局部信息计算方法,改为以搜索窗口尺寸为循环,利用空间位移图像与递归高斯滤波的计算方法,克服非局部空间信息计算复杂的问题;其次,计算原始图像与非局部信息项的差值的平方,将其作为非局部信息项的自适应权重,并将差值的平方作倒数变换,作为原始图像的自适应权重;最后,将每个聚类簇中所有像素隶属度之和的对数平方加入目标函数的分母,形成隶属度连接,减少目标函数迭代次数。含噪人工与自然图像分割实验表明,该算法在分割准确度、平均交并比、归一化互信息、运行时间与迭代次数等性能方面优于其他几种FCM算法。

  • 图  1  5种算法对含5%混合噪声人工图像的分割结果(K=4)

    图  2  5种算法对含20%混合噪声齿轮图像的分割结果(K=2)

    图  3  5种算法对含10%混合噪声#42049的分割结果(K=2)

    图  4  5种算法对含10%混合噪声#86016的分割效果(K=2)

    图  5  5种算法对含5%混合噪声#118035的分割效果(K=3)

    表  1  5种算法对含不同混合噪声人工图像的分割结果

    分割指标SA(%)mIoU(%)NMI(%)运行时间(s)迭代次数
    噪声大小(%)51015205101520510152051015205101520
    FCM55.0943.7731.2128.2152.6548.4835.4130.4125.3414.429.097.130.480.630.670.6918363235
    FLICM89.5470.8960.0052.0884.9564.2555.1649.5173.3250.1038.7130.907.527.947.238.02108125106130
    FCM-NLS96.8391.4876.2659.4396.3587.4068.4647.8085.9376.9753.6338.10185.57194.82195.57195.1424334747
    SNLS-IFCM97.6692.2377.0461.0296.6788.7570.1254.5986.0079.1857.8340.13184.12196.07196.40196.8317405173
    本文算法98.0297.3095.2690.1297.7095.5492.4086.7192.2389.8884.3574.841.851.922.092.0910101617
    下载: 导出CSV

    表  2  5种算法对含不同混合噪声图像的分割结果

    分割指标SA(%)mIoU(%)NMI(%)运行时间(s)迭代次数
    噪声大小(%)51015205101520510152051015205101520
    FCM90.5881.8274.5770.8882.6068.8858.8254.4154.9931.4217.8012.320.180.200.150.1815161618
    71.5663.1658.7455.8351.1642.7438.7436.2615.74 7.56 4.50 3.020.460.440.350.2223211611
    61.8757.5154.0451.5140.9636.5234.0332.04 8.19 3.27 2.22 1.330.370.580.280.3418191416
    55.8749.2346.7723.5036.5030.7328.1212.3519.45 9.96 6.11 4.111.020.760.520.7035251723
    FLICM98.8398.1196.6894.4197.6896.2793.5289.3690.8086.4478.9069.031.604.523.664.29647988109
    95.3393.1990.7688.6186.3180.9275.3970.9063.8152.8642.4634.6312.3211.4113.6916.14158148177212
    92.1992.8885.8284.0778.5978.1065.4561.0852.9146.0128.0219.9813.229.5823.6122.00157100300300
    62.1554.5344.4537.2046.3539.2030.8524.9949.0137.8127.2120.4718.8523.1718.4713.09132194151108
    FCM-NLS98.8498.1697.3895.8797.6896.3594.8491.9890.9886.9482.9076.62189.77190.08188.92197.1213161625
    95.3093.5383.5271.6286.2682.3965.3751.4963.6955.4231.1717.26472.53474.82468.91473.5129293630
    96.1384.8571.7063.3988.0065.1250.8842.7370.8537.3421.1511.77473.12470.12454.68472.6829283128
    85.8579.3172.2261.2567.4860.0852.3141.8462.8255.3644.6336.43478.75473.25479.75480.7535534949
    SNLS-IFCM98.9298.0597.3195.5097.8396.1494.7091.2991.4386.4082.5075.51188.42189.15188.50196.3011121318
    96.7593.8984.7272.6189.6482.8667.0152.5673.5756.6733.0318.48470.25465.61470.42472.7620254231
    96.8086.2171.9663.0189.7665.5151.2142.4979.8141.5521.9912.23470.30468.14452.14467.1423202824
    87.9279.3371.6363.1170.8059.8751.7243.8665.7854.1544.7235.16474.25471.81470.25472.2530392435
    本文算法99.2398.2697.4096.8998.1296.5595.1993.9092.0787.7083.5481.321.752.061.901.806668
    98.8994.3694.3493.4096.0484.5583.4582.1587.0161.0658.2755.884.534.414.784.447121413
    98.9797.7297.4691.8796.3192.3491.3878.1087.7978.3275.4453.154.535.514.534.37710711
    90.7187.4087.8279.0672.7566.2767.8560.0369.8465.5863.1354.464.864.374.814.9297917
    下载: 导出CSV

    表  3  5种算法的时间复杂度

    分割算法计算步骤$E$计算步骤函数$E(n)$时间复杂度
    FCM$H \times W \times K \times {\rm{iter} }$${n^4}$$O({n^4})$
    FLICM$H \times W \times K \times {k^2} \times {\rm{iter} }$${n^6}$$O({n^6})$
    FCM-NLS$H \times W \times {(2S + 1)^2} \times {(2s + 1)^2} + H \times W \times K \times {\rm{iter} }$${n^2}{(n + 1)^4} + {n^4}$$O({n^6})$
    SNLS-IFCM$H \times W \times {(2S + 1)^2} \times {(2s + 1)^2} + H \times W \times (K - 1) \times K \times {\rm{iter} }$${n^2}{(n + 1)^4} + {n^4}(n - 1)$$O({n^6})$
    本文算法$H \times W \times [{(2S + 1)^2} - 1] + (2 \times H \times W) \times K \times {\rm{iter} }$${n^2}[{(n + 1)^2} - 1] + 2{n^4}$$O({n^4})$
    下载: 导出CSV
  • 范九伦, 雷博. 倒数粗糙熵图像阈值化分割算法[J]. 电子与信息学报, 2020, 42(1): 214–221. doi: 10.11999/JEIT190559

    FAN Jiulun and LEI Bo. Image thresholding segmentation method based on reciprocal rough entropy[J]. Journal of Electronics &Information Technology, 2020, 42(1): 214–221. doi: 10.11999/JEIT190559
    许新征, 丁世飞, 史忠植, 等. 图像分割的新理论和新方法[J]. 电子学报, 2010, 38(2A): 76–82.

    XU Xinzheng, DING Shifei, SHI Zhongzhi, et al. New theories and methods of image segmentation[J]. Acta Electronica Sinica, 2010, 38(2A): 76–82.
    姜枫, 顾庆, 郝慧珍, 等. 基于内容的图像分割方法综述[J]. 软件学报, 2017, 28(1): 160–183. doi: 10.13328/j.cnki.jos.005136

    JIANG Feng, GU Qing, HAO Huizhen, et al. Survey on content-based image segmentation methods[J]. Journal of Software, 2017, 28(1): 160–183. doi: 10.13328/j.cnki.jos.005136
    申铉京, 刘翔, 陈海鹏. 基于多阈值Otsu准则的阈值分割快速计算[J]. 电子与信息学报, 2017, 39(1): 144–149. doi: 10.11999/JEIT160248

    SHEN Xuanjing, LIU Xiang, and CHEN Haipeng. Fast computation of threshold based on multi-threshold Otsu criterion[J]. Journal of Electronics &Information Technology, 2017, 39(1): 144–149. doi: 10.11999/JEIT160248
    KHAIRE P A and THAKUR N V. An overview of image segmentation algorithms[J]. International Journal of Image Processing and Vision Sciences, 2012, 1(2): 62–68.
    雷涛, 张肖, 加小红, 等. 基于模糊聚类的图像分割研究进展[J]. 电子学报, 2019, 47(8): 1776–1791. doi: 10.3969/j.issn.0372-2112.2019.08.023

    LEI Tao, ZHANG Xiao, JIA Xiaohong, et al. Research progress on image segmentation based on fuzzy clustering[J]. Acta Electronica Sinica, 2019, 47(8): 1776–1791. doi: 10.3969/j.issn.0372-2112.2019.08.023
    WAZARKAR S and KESHAVAMURTHY B N. A survey on image data analysis through clustering techniques for real world applications[J]. Journal of Visual Communication and Image Representation, 2018, 55: 596–626. doi: 10.1016/j.jvcir.2018.07.009
    ZADEH L A. Fuzzy sets[J]. Information and Control, 1965, 8(3): 338–435. doi: 10.1016/S0019-9958(65)90241-X
    FAN Jiulun, ZHEN Wenzhi, and XIE Weixin. Suppressed fuzzy c-means clustering algorithm[J]. Pattern Recognition Letters, 2003, 24(9/10): 1607–1612. doi: 10.1016/S0167-8655(02)00401-4
    AHMED M N, YAMANY S M, MOHAMED N, et al. A modified fuzzy C-means algorithm for bias field estimation and segmentation of MRI data[J]. IEEE Transactions on Medical Imaging, 2002, 21(3): 193–199. doi: 10.1109/42.996338
    ZHU Lin, CHUNG F L, and WANG Shitong. Generalized fuzzy C-means clustering algorithm with improved fuzzy partitions[J]. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics) , 2009, 39(3): 578–591. doi: 10.1109/TSMCB.2008.2004818
    KRINIDIS S and CHATZIS V. A robust fuzzy local information c-means clustering algorithm[J]. IEEE Transactions on Image Processing, 2010, 19(5): 1328–1337. doi: 10.1109/TIP.2010.2040763
    ZHAO Feng, JIAO Licheng, and LIU Hanqiang. Fuzzy c-means clustering with non local spatial information for noisy image segmentation[J]. Frontiers of Computer Science in China, 2011, 5(1): 45–56. doi: 10.1007/s11704-010-0393-8
    CHEN Songcan and ZHANG Daoqiang. Robust image segmentation using FCM with spatial constraints based on new kernel-induced distance measure[J]. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics) , 2004, 34(4): 1907–1916. doi: 10.1109/TSMCB.2004.831165
    ZHAO Feng. Fuzzy clustering algorithms with self-tuning non-local spatial information for image segmentation[J]. Neurocomputing, 2013, 106: 115–125. doi: 10.1016/j.neucom.2012.10.022
    兰蓉, 林洋. 抑制式非局部空间直觉模糊C-均值图像分割算法[J]. 电子与信息学报, 2019, 41(6): 1472–1479. doi: 10.11999/JEIT180651

    LAN Rong and LIN Yang. Suppressed non-local Spatial intuitionistic fuzzy C-means image segmentation algorithm[J]. Journal of Electronics &Information Technology, 2019, 41(6): 1472–1479. doi: 10.11999/JEIT180651
    施伟锋, 卓金宝, 兰莹. 一种基于属性空间相似性的模糊聚类算法[J]. 电子与信息学报, 2019, 41(11): 2722–2728. doi: 10.11999/JEIT180974

    SHI Weifeng, ZHUO Jinbao, and LAN Ying. A novel fuzzy clustering algorithm based on similarity of attribute space[J]. Journal of Electronics &Information Technology, 2019, 41(11): 2722–2728. doi: 10.11999/JEIT180974
    GONG Maoguo, LIANG Yan, SHI Jiao, et al. Fuzzy C-means clustering with local information and kernel metric for image segmentation[J]. IEEE Transactions on Image Processing, 2013, 22(2): 573–584. doi: 10.1109/TIP.2012.2219547
    ELAZAB A, WANG Changmiao, JIA Fucang, et al. Segmentation of brain tissues from magnetic resonance images using adaptively regularized kernel-based fuzzy C-means clustering[J]. Computational and Mathematical Methods in Medicine, 2015, 2015: 485495. doi: 10.1155/2015/485495
    MEMON K H and LEE D H. Generalised kernel weighted fuzzy C-means clustering algorithm with local information[J]. Fuzzy Sets and Systems, 2018, 340: 91–108. doi: 10.1016/j.fss.2018.01.019
    BUADES A, COLL B, and MOREL J M. A non-local algorithm for image denoising[C]. 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Diego, USA, 2005: 60–65. doi: 10.1109/CVPR.2005.38.
    VAN VLIET L J, YOUNG I T, and VERBEEK P W. Recursive Gaussian derivative filters[C]. The 14th International Conference on Pattern Recognition, Brisbane, Australia, 1998: 509–514. doi: 10.1109/ICPR.1998.711192.
  • 加载中
图(5) / 表(3)
计量
  • 文章访问数:  1320
  • HTML全文浏览量:  443
  • PDF下载量:  334
  • 被引次数: 0
出版历程
  • 收稿日期:  2019-12-19
  • 修回日期:  2020-11-04
  • 网络出版日期:  2020-11-07
  • 刊出日期:  2021-01-15

目录

    /

    返回文章
    返回