计算机科学 ›› 2021, Vol. 48 ›› Issue (8): 111-117.doi: 10.11896/jsjkx.200700003

• 计算机图形学& 多媒体 • 上一篇    下一篇

融合Tamura纹理特征的改进FCM脑MRI图像分割算法

乔颖婧, 高保禄, 史瑞雪, 刘璇, 王朝辉   

  1. 太原理工大学软件学院 山西 晋中030600
  • 收稿日期:2020-07-01 修回日期:2020-08-13 发布日期:2021-08-10
  • 通讯作者: 高保禄(85389301@qq.com)
  • 基金资助:
    国家重点研发计划(2018YFB2200900);国家自然科学基金项目(61772358)

Improved FCM Brain MRI Image Segmentation Algorithm Based on Tamura Texture Feature

QIAO Ying-jing, GAO Bao-lu, SHI Rui-xue, LIU Xuan, WANG Zhao-hui   

  1. College of Software,Taiyuan University of Technology,Jinzhong,Shanxi 030600,China
  • Received:2020-07-01 Revised:2020-08-13 Published:2021-08-10
  • About author:QIAO Ying-jing,born in 1995,postgra-duate.Her main research interests include intelligent & adaptive control and image processing.(2068195322@qq.com)GAO Bao-lu,born in 1971,Ph.D,lectu-rer,postgraduate supervisor.His main research interests include intelligent information processing and image processing.
  • Supported by:
    National Key Research and Development Program of China(2018YFB2200900) and National Natural Science Foundation of China(61772358).

摘要: 针对FCM算法在分割脑MRI图像时存在噪声敏感性和初始聚类中心随机性的问题,提出一种融合图像Tamura纹理特征的改进FCM图像分割算法。首先提取图像的Tamura纹理特征,将其与灰度特征线性加权构成融合特征。然后使用模糊邻域关系计算像素点的密度,将其与距离关系结合自适应选取初始聚类中心。最后使用融合特征作为更新隶属度和聚类中心的特征约束。实验利用该方法与FCM,D-FCM,WKFCM方法对Brain Web脑MRI数据集中的图像进行分割,并在抗噪性、准确性和运行效率方面进行了比较。实验结果表明,所提算法能获取更优的初始聚类中心,在处理噪声和灰度不均匀图像上表现出更好的鲁棒性,能够快速有效地分割脑MRI图像。

关键词: 模糊聚类, 磁共振影像, Tamura纹理信息, 线性融合, 初始聚类中心

Abstract: To solve the problems of noise sensitivity and initial clustering center randomness in the segmentation of brain MRI images by FCM algorithm,an improved FCM image segmentation algorithm based on Tamura texture feature is proposed.Firstly,the Tamura texture feature of the image is extracted,and it is linearly weighted with the gray feature to form a fusion feature.Then,the density of pixel is calculated by using fuzzy neighborhood relation,and the initial cluster center is selected by combining it with distance relation.Finally,the fusion feature is used as a feature constraint for updating membership and clustering center.In the experiment,FCM,D-FCM,WKFCM and the proposed method are used to segment the images in Brain Web MRI dataset,and their anti-noise performance,accuracy and operation efficiency are compared.Experimental results show that the proposed algorithm can obtain better initial clustering centers,has better robustness in processing noise and gray inhomogeneity images,and can segment brain MRI images quickly and effectively.

Key words: Fuzzy clustering, Magnetic resonance imaging, Tamura texture information, Linear fusion, Initial cluster center

中图分类号: 

  • TP751
[1]KOUHI A,SEYEDARABI H,AGHAGOLZADEH A.Robust FCM clustering algorithm with combined spatial constraint and membership matrix local information for brain MRI segmentation[J].Expert Systems with Applications,2019,146:113159.
[2]ALRUWAILI M,SIDDIQI M H,JAVED M A.A robust clustering algorithm using spatial fuzzy C-means for brain MR images[J].Egyptian Informatics Journal,2019,21(1):51-66.
[3]GHOSH P,MALI K,DAS S K.Chaotic firefly algorithm-based fuzzy C-means algorithm for segmentation of brain tissues in magnetic resonance images[J].Journal of Visual Communication &Image Representation,2018,54(JUL.):63-79.
[4]LU H Q,GE H W.Fuzzy C-means Method for Brain Magnetic Resonance Image Segmentation and Bias Field Correction[J].Journal of Chongqing University of Posts and Telecommunications(Natural Science Edition),2018,30(4):518-529.
[5]WADHWA A,BHARDWAJ A,SINGH V.A review on brain tumor segmentation of MRI images[J].Magnetic Resonance Imaging,2019,61:247-259.
[6]LIU J,LI M,WANG J X,et al.A survey of MRI-based brain tumor segmentation methods[J].Tsinghua Science and Technology,2014,19(6):578-595.
[7]DING X F,HE K L.A Homogeneous Pieces based FCM Algorithm for Image Segmentation[J].Journal of Chongqing University of Posts and Telecommunications(Natural Science Edition),2017,29(3):377-381.
[8]WANGW N,MA Y,JIANG Y T,et al.Research on fuzzy clustering image segmentation algorithm based on fractional particle swarm optimization[J].Modern Electronics Technique,2019,42(11):59-63.
[9]GUO L,CHEN L,CHEN C L P,et al.Integrating guided filter into fuzzy clustering for noisy image segmentation[J].Digital Signal Processing,2018,83:235-248.
[10]ALIPOUR S,SHANBEHZADEH J.Fast automatic medical ima-ge segmentation based on spatial kernel fuzzy c-means on level set method[J].Machine Vision & Applications,2014,25(6):1469-1488.
[11]ADHIKARI S K,SING J K,BASU D K,et al.Conditional spatial fuzzy C-means clustering algorithm for segmentation of MRI images[J].Applied Soft Computing,2015,34:758-769.
[12]PEI H X,ZHENG Z R,WANG C,et al.D-FCM:Density based fuzzy c-means clustering algorithm with application in medical image segmentation[J].Procedia Computer Science,2017,122:407-414.
[13]REN T B,WANG H H,FENG H L.Study on the improvedfuzzy clustering algorithm and its application in brain image segmentation[J].Applied Soft Computing Journal,2019,81:105503.
[14]YU W Y,KANG X D,GE W J,et al.Image Classification and Identification through SVM Based on Fuzzy Kernel Clustering [J].Computer Science,2015,42(3):307-310.
[15]TAMURA H,MORI S,YAMAWAKI T.Textural FeaturesCorresponding to Visual Perception[J].IEEE Transactions on Systems Man & Cybernetics,1978,8(6):460-473.
[16]DU M,DING S,XUE Y.A robust density peaks clustering algorithm using fuzzy neighborhood[J].International Journal of Machine Learning & Cybernetics,2017,9(7):1131-1140.
[17]LIU C,WU C M.Robust picture fuzzy clustering segmentation algorithm based on fractional information[J].Computer Engineering and Design,2019,40(3):774-781,855.
[18]SINGH C,BALA A.A DCT-based local and non-local fuzzy C-means algorithm for segmentation of brain magnetic resonance images[J].Applied Soft Computing,2018,68:447-457.
[19]LAI J,ZHU H,LING X.Segmentation of Brain MR Images by Using Fully Convolutional Network and Gaussian Mixture Mo-del with Spatial Constraints[J].Mathematical Problems in Engineering,2019,2019:1-14.
[20]SHANKER R,BHATTACHARYA M.Brain tumor segmentation of normal and pathological tissues using K-mean clustering with fuzzy C-mean clustering[J].Lecture Notes in ComputationalVision and Biomechanics,2017,27:286-296.
[1] 张天柱, 邹承明. 使用模糊聚类的胶囊网络在图像分类上的研究[J]. 计算机科学, 2019, 46(12): 279-285.
[2] 冀进朝,赵晓威,何飞,胡英慧,白天,李在荣. 基于模糊质心的混合属性数据模糊加权聚类算法[J]. 计算机科学, 2018, 45(2): 109-113.
[3] 邢瑞康, 李成海. 基于直觉模糊集理论的IDS方法研究[J]. 计算机科学, 2018, 45(11A): 344-348.
[4] 王宏杰,师彦文. 结合初始中心优化和特征加权的K-Means聚类算法[J]. 计算机科学, 2017, 44(Z11): 457-459.
[5] 郑奇斌,刁兴春,曹建军. 结合缺失模式的不完整数据模糊聚类[J]. 计算机科学, 2017, 44(12): 58-63.
[6] 耿宗科,王长宾,张振国. 基于模糊c-means与自适应粒子群优化的模糊聚类算法[J]. 计算机科学, 2016, 43(8): 267-272.
[7] 陈小东,孙力娟,韩崇,郭剑. 基于模糊聚类的数据流概念漂移检测算法[J]. 计算机科学, 2016, 43(4): 219-223.
[8] 冯晨菲,杨燕,王红军,徐英歌,王韬. 一种基于数据相关性的半监督模糊聚类集成方法[J]. 计算机科学, 2015, 42(6): 41-45.
[9] 郭华峰,赵建民,潘修强. 自适应抑制式模糊C-回归模型算法[J]. 计算机科学, 2015, 42(2): 274-276.
[10] 董世龙,陈宁江,谭瑛,何子龙,朱莉蓉. 面向云环境的集群资源模糊聚类划分算法的优化[J]. 计算机科学, 2014, 41(9): 104-109.
[11] 张千,梁鸿,郉永山. 云计算环境下基于模糊聚类的并行调度策略研究[J]. 计算机科学, 2014, 41(8): 75-80.
[12] 沈洁,郭莉森. 社会网络的模糊聚类理论及其实践[J]. 计算机科学, 2013, 40(Z11): 63-67.
[13] 刘颖,张柏,王爱莲,桑娟,何咏梅. 一种基于半监督集成SVM的土地覆盖分类模型[J]. 计算机科学, 2013, 40(7): 206-210.
[14] 李栓栓,李成海,郭新鹏. 基于模糊等价矩阵的无线传感器聚类分区算法[J]. 计算机科学, 2012, 39(Z6): 123-124.
[15] 王纵虎,刘志镜,陈东辉. 基于粒子群优化的模糊C一均值聚类算法研究[J]. 计算机科学, 2012, 39(9): 166-169.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] 孙启,金燕,何琨,徐凌轩. 用于求解混合车辆路径问题的混合进化算法[J]. 计算机科学, 2018, 45(4): 76 -82 .
[2] 耿海军,施新刚,王之梁,尹霞,尹少平. 基于有向无环图的互联网域内节能路由算法[J]. 计算机科学, 2018, 45(4): 112 -116 .
[3] 邓霞, 常乐, 梁俊斌, 蒋婵. 移动机会网络组播路由的研究进展[J]. 计算机科学, 2018, 45(6): 19 -26 .
[4] 张昱, 高克宁, 于戈. 一种融合节点属性信息的社会网络链接预测方法[J]. 计算机科学, 2018, 45(6): 41 -45 .
[5] 胡雅鹏, 丁维龙, 王桂玲. 一种面向异构大数据计算框架的监控及调度服务[J]. 计算机科学, 2018, 45(6): 67 -71 .
[6] 张盼盼, 彭长根, 郝晨艳. 一种基于隐私偏好的隐私保护模型及其量化方法[J]. 计算机科学, 2018, 45(6): 130 -134 .
[7] 成静, 张涛, 王涛, 董占伟. 一种基于图复杂度的移动导航服务回归测试优先方法[J]. 计算机科学, 2018, 45(6): 141 -144 .
[8] 徐晓玲, 金忠, 贲圣兰. 基于标签敏感最大间隔准则的人脸年龄两步估计算法[J]. 计算机科学, 2018, 45(6): 284 -290 .
[9] 任晖,戴华,杨庚. 基于安全比较码的云环境隐私保护排序方法[J]. 计算机科学, 2018, 45(5): 139 -142 .
[10] 耿焕同,丁洋洋,周利发,韩伟民. 一种基于自适应选择策略的改进型MOEA/D算法[J]. 计算机科学, 2018, 45(5): 201 -207 .