利用高斯混合模型的多光谱图像模糊聚类分割

李玉; 徐艳; 赵雪梅; 赵泉华

doi:10.3788/OPE.20172402.0509

您当前的位置：

首页 >

文章列表页 >

利用高斯混合模型的多光谱图像模糊聚类分割

信息科学 | 更新时间：2020-07-07

- 利用高斯混合模型的多光谱图像模糊聚类分割
- Multispectral image segmentation by fuzzy clustering algorithm used Gaussian mixture model
- 光学精密工程 2017年25卷第2期页码：509-518
- 作者机构：
  
  辽宁工程技术大学测绘与地理科学学院遥感科学与应用研究所, 辽宁阜新 123000
- 作者简介：
  
  李玉 (1963-)，男，吉林长春人，博士，教授, 1984年于西北电讯工程学院获得学士学位，1991年于东南大学获得硕士学位，2006年于瑞尔森获得硕士学位，2010年于滑铁卢大学获得博士学位，主要研究方向为遥感数据处理理论与应用基础研究，包括空间统计学随机几何模糊数学在遥感数据建模与分析方面的应用，地物目标几何以及特征提取。E-mail:lntuliyu@163.com LI Yu, E-mail: E-mail:Intuliyu@163.com
  [ "徐艳 (1991-), 女, 山西朔州人, 硕士研究生, 2015年于辽宁工程技术大学获得学士学位, 主要研究方向为模糊聚类及其在遥感图像处理中的应用。E-mail:2425207748@qq.com" ]
- 基金信息：
  
  国家自然科学基金青年基金资助项目(41301479);国家自然科学基金面上项目(41271435);辽宁省自然科学基金资助项目(2015020090)
- DOI：10.3788/OPE.20172402.0509
  中图分类号： TP79
- 收稿日期：2016-08-25，
  
  录用日期：2016-11-4，
  
  纸质出版日期：2017-02-25
- 稿件说明：
移动端阅览
李玉, 徐艳, 赵雪梅, 等. 利用高斯混合模型的多光谱图像模糊聚类分割[J]. 光学精密工程, 2017,25(2):509-518.

Yu LI, Yan XU, Xue-mei ZHAO, et al. Multispectral image segmentation by fuzzy clustering algorithm used Gaussian mixture model[J]. Optics and precision engineering, 2017, 25(2): 509-518.
李玉, 徐艳, 赵雪梅, 等. 利用高斯混合模型的多光谱图像模糊聚类分割[J]. 光学精密工程, 2017,25(2):509-518. DOI： 10.3788/OPE.20172402.0509.

Yu LI, Yan XU, Xue-mei ZHAO, et al. Multispectral image segmentation by fuzzy clustering algorithm used Gaussian mixture model[J]. Optics and precision engineering, 2017, 25(2): 509-518. DOI： 10.3788/OPE.20172402.0509.

摘要

针对传统分割算法难以实现高分辨率多光谱图像分割的问题，本文提出一种利用高斯混合模型的多光谱图像模糊聚类分割算法。该算法采用高斯混合模型定义像素对类属的非相似性测度，由于该算法具有高精度拟合数据统计分布能力，故可以有效剔除噪声对分割结果的影响。同时，引入隐马尔科夫随机场（Hidden Markov Random Field，HMRF）定义邻域作用的先验概率，并将其作为各高斯分量权值以及KL（Kullback-Leibler）信息中控制聚类尺度的参数，从而增强了算法对复杂场景遥感图像的鲁棒性，进一步提高了算法的分割精度。对模拟图像和高分辨多光谱图像分割结果进行了定性定量分析。实验结果表明：模拟图像的总精度达96.8%以上。这验证了本文算法在分割高分辨率多光谱图像时具有保留细节信息的能力，而且也证实了算法的有效性和可行性。该算法能够实现高分辨率多光谱图像的精确分割。

Abstract

As the traditional segmentation algorithms are difficult to realize accurate segmentation for high resolution multispectral image

this paper proposed a kind of fuzzy clustering segmentation algorithm of multispectral image on the basis of Gaussian mixture model (GMM). GMM was adopted to define the dissimilarity measure of pixels to the clusters.As the proposed algorithm has the ability of high-precision fitting data statistics distribution

it can effectively eliminate the negative impact of noise on segmentation results. Hidden Markov Random Field (HMRF) was brought in to define prior probability of neighborhood relationship simultaneously

then the prior probability was used as weight of each Gaussian component and parameter to control cluster scale in Kullback-Leibler (KL)

so the robustness of algorithm to remote sensing image at complex scene was increased and segmentation accuracy of algorithm was further improved. Qualitative and quantitative analysis were conducted on segmentation result of simulated image and high resolution multispectral image. Experimental result shows that the total accuracy of simulated image exceeds 96.8%

which verifies that algorithm mentioned has detailed information keeping capacity when performing segmentation to high resolution multispectral image and verifies effectiveness and feasibility of algorithm. The algorithm can realize accurate segmentation of the high resolution multispectral image.

关键词

Keywords

references

PASQUA D, GAETANO T. Solution of a Mbrosio-Tortorelli model for image segmentation by generalized relaxation method[J]. Communications in Nonlinear Science and Numerical Simulation, 2015, 20(3):819-831.

刘永学, 李满春, 毛亮.基于边缘的多光谱遥感图像分割方法[J].遥感学报, 2006, 10(3):350-356.

LIU Y X, LI M CH, MAO L. An algorithm of multispectral remote sensing image segmentation based on edge information[J]. Journal of Remote Sensing, 2006, 10(3):350-356. (in Chinese)

徐春燕, 冯学智, 赵书河, 等.基于数字形态学的IKONOS多光谱图像分割方法研究[J].遥感学报, 2008, 12(6):980-986.

XV CH Y, FENG X ZH, ZHAO S H, et al.. Mathematical morphological segmentation of IKONOS multispectral data[J]. Journal of Remote Sensing, 2008, 12(6):980-986. (in Chinese)

COLENMAN G B, ANDREWS H C. Image segmentation by clustering[J]. Institute of Electrical and Electronics Engineers, 1979, 67(5):773-785.

DUNN J C. Well-separated clusters and the optimal fuzzy partitions[J]. Journal of Cybernetics, 2008, 4(1):95-104.

BEZDEK J C. Pattern recognition with fuzzy objective function algorithms[A]. New York:Plenum Press, 1981, 1171(22):43-60.

MIYAMOTO S, MUKAIDONO M. Fuzzy c-means as a regularization and maximum entropy approach[C]. Proceedings of the 7th IFSA Conference, 1997:86-92.

田军委, 黄永宣, 于亚琳.基于熵约束的快速FCM聚类多阈值图像分割算法[J].模式识别与人工智能, 2008, 21(2):221-226.

TIAN J W, HUANG Y X, YU Y L. A fast FCM cluster multi-threshold image segmentation algorithm based on entropy constraint[J]. Pattern Recognition and Artificial Intelligence, 2008, 21(2):221-226. (in Chinese)

王士龙, 徐玉如, 万磊, 等.一种基于信息熵约束的快速FCM聚类水下图像分割算法[J].计算机科学, 2010, 37(12):243-246+286.

WANG SH L, XU Y R, WAN L, et al.. Fast fuzzy C-means algorithm based on entropy constraint for underwater image segmentation[J]. Computer Science, 2010, 37(12):243-246+286. (in Chinese)

尹诗白, 王一斌, 邓箴.基于快速递推模糊2-划分熵的红外图像分割[J].光学精密工程, 2016, 24(3):668-680.

YIN SH B, WANG Y B, DEND ZH. Infrared image segmentation based on graph cut of fast recursive fuzzy 2-partition entropy[J]. Opt. Precision Eng., 2016, 24(3):668-680. (in Chinese)

ICHIHASHI H, MIYAGISHI K, HONDA K. Fuzzy c-means clustering with regularization by KL information[C]. Institute of Electrical and Electronics Engineers International Conference on Fuzzy Systems, 2001, 13(4):924-927.

ZHENG Q, LU Z T, YANG W, et al.. A robust medical image segmentation method using KL distance and local neighborhood information[J]. Computers in Biology and Medicine, 2013, 43(5):459-470.

赵维兵.中巴地球资源卫星图像中伪"同谱异物"区分方法研究[J].遥测遥控, 2008, 29(2):19-25.

ZHAO W B. Research on the method of differentiating false "different objects same image" in the CBERS image[J]. Journal of Telemetry, Tracking and Command, 2008, 29(2):19-25. (in Chinese).

王和春, 宫迅凯.用模糊聚类Fuzzy C-means算法实现图像分割[J].光学精密工程, 1991, 4:65-70.

WANG H C, GONG X K. Image segmentation by fuzzy C-means clustering algorithm[J]. Opt. Precision Eng., 1991, 4:65-70. (in Chinese)

JING F, CHE R, WANG J. Recognition of remote sensing images in the three gorges reservoir area by fuzzy C-means clustering algorithm based on Mahalanobis distance[C]. Second Lita International Conference on Geoscience & Remote Sensing, 2010, 2:154-156.

田杰, 胡秋霞, 马孝义.基于高斯分布改进C-V模型的植物病斑彩色图像分割[J].农业工程学报, 2013, 29(16):166-173.

TIAN J, HU Q X, MA X Y. Color image segmentation of plant lesion using improved C-V model based on Gaussian distribution[J]. Transactions of the Chinese Society of Agricultural Engineering, 2013, 29(16):166-173. (in Chinese)

崔文超, 王毅, 樊养余, 等.局部高斯分布拟合的脑MR图像分割以及有偏场校正[J].中国图象图形学报, 2013, 18(5):552-557.

CUI W CH, WANG Y, FAN Y Y, et al.. Multiphase level set method for segmentation and bias correction of brain MR images[J]. Journal of Image and Graphics, 2013, 18(5):552-557. (in Chinese)

朱峰, 罗立民, 宋余庆, 等.基于自适应空间邻域信息高斯混合模型的图像分割[J].计算机研究与发展, 2011, 44(11):2000-2007.

ZHU F, LUO L M, SONG Y Q, et al.. Adaptive spatially neighborhood information Gaussian mixture model for image segmentation[J]. Journal of Computer Research and Development, 2011, 44(11):2000-2007. (in Chinese)

王醒策, 文蕾, 武仲科, 等.面向时飞磁共振血管造影术的脑血管统计分割混合模型[J].光学精密工程. 2014, 22(2):497-507.

WANG X C, WEN L, WU ZH K, et al.. Finite mixture model of stochastic cerebrovascular segmentation based on TOF MRA[J]. Opt. Precision Eng., 2014, 22(2):497-507. (in Chinese)

赵雪梅, 李玉, 赵泉华.结合马尔可夫高斯模型的双邻域模糊聚类分割算法[J].计算机辅助设计与图形学学报. 2016, 28(4):614-622.

ZHAO X M, LI Y, ZHAO Q H. A fuzzy clustering image segmentation algorithm with double neighborhood system combined with Markov Gaussian model[J]. Journal of Computer-aided Design & Computer Graphics, 2016, 28(4):614-622. (in Chinese)

赵雪梅, 李玉, 赵泉华.基于隐马尔可夫高斯随机场模型的模糊聚类高分辨率遥感影像分割算法[J].电子学报, 2016, 44(3):679-686.

ZHAO X M, LI Y, ZHAO Q H. Hidden Markov Gaussian random field based fuzzy clustering algorithm for high-resolution remote sensing image segmentation[J]. Chinese Journal of Electronics, 2016, 44(3):679-686. (in Chinese)

宫改云, 高新波, 伍忠东. FCM聚类算法中模糊加权指数m的优选方法[J].模糊系统与数学, 2005, 19(1):143-148.

GONG G Y, GAO X B, WU ZH D. An optimal choice method of parameter m in FCM clustering algorithm[J]. Fuzzy Systems and Mathematics, 2005, 19(1):143-148. (in Chinese)

高新波, 谢维信.模糊聚类理论发展及应用的研究进展[J].科学通报, 1999, 44(21):2241-2251.

GAO X B, XIE W X. Development and application of fuzzy cluster theory[J]. Chinese Science Bulletin, 1999, 44(21):2241-2251. (in Chinese)

杨润玲.基于FCM类型算法的自动图像分割方法研究[D].西安:西安电子科技大学, 2006.

YANG R L. Automatic image segmentation method based on the type of FCM algorithm research[D]. Xi'an:Xidian University, 2006. (in Chinese)

BEZDEK J C, A physical interpretation of fuzzy ISODATA[J]. Institute of Electrical and Electronics Engineer, 1976, 6(5):387-390.

PAL N R, BEZDEK J C. On cluster validity for the fuzzy c-means model[J]. Institute of Electrical and Electronics Engineer Fuzzy Systems, 1995, 3(3):370-379.

刘燕杰, 卢振泰, 冯前进, 等.基于KL距离加权和局部邻域信息的CV模型[J].电子学报, 2011, 39(6):1447-1451.

LIU Y J, LU ZH T, FENG Q J, et al.. KL distance weighted CV model based on local neighborhood information[J]. Acta Electronica Sinica, 2011, 39(6):1447-1451. (in Chinese)

HONDA K, OSHIO S, NOTSU A. FCM-type fuzzy co-clustering by K-L information regularization[C]. Institute of Electrical and Electronics Engineers International Conference on Fuzzy Systems, 2014:2505-2510.

蒋璐媛, 肖鹏峰, 冯学智, 等.基于亚分数混淆矩阵的中国典型区大尺度土地覆盖数据集评价[J].遥感技术与应用, 2015, 33(2):353-363.

JIANG L Y, XIAO P F, FENG X ZH, et al.. Assessment of large scale land cover datasets in typical areas of China based on sub-fractional error matrix[J]. Remote Sensing Technology and Application, 2015, 33(2):353-363. (in Chinese)

浏览量

107

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

融合条形注意力机制的电芯极片计算机断层图像分割

增强型金枪鱼群优化指数熵的砂粒显微图像分割

语义流引导采样结合注意力机制的脑肿瘤图像分割

混沌SSA优化多重熵阈值的骨料图像自动分割

基于高分辨率复合网络的皮肤病变分割