首页 | 本学科首页   官方微博 | 高级检索  
     

基于像元相互关系的FCM聚类分割算法
引用本文:周友行,刘汉江,赵晗妘,赵玉.基于像元相互关系的FCM聚类分割算法[J].仪器仪表学报,2019,40(9):124-131.
作者姓名:周友行  刘汉江  赵晗妘  赵玉
作者单位:湘潭大学机械工程学院
基金项目:国家自然科学基金项目(面上项目,重点项目,重大项目),中国博士后科学基金
摘    要:针对传统模糊C均值(FCM)算法在图像分割时未考虑像元间的相互关系,且未事先给出初始聚类中心的问题,提出了一种考虑像元间相互关系的FCM聚类分割算法。该算法基于数据场原理,首先利用像元间的相互关系,通过计算各像素点的势值,形成图像数据场,然后利用图像数据场势心,确定FCM算法的初始聚类中心,最后在图像数据场的基础上,利用FCM算法实现对目标图像的聚类分割。利用人工合成图像和工件表面缺陷图像对算法的有效性进行验证,实验结果表明,该算法具有较好的分割效果,且对于条痕、脱碳、孔洞3种缺陷的不同噪声图像分割的正确率均在93%以上,同时具有较高的平均结构相似性。

关 键 词:图像分割  数据场  模糊C均值  表面缺陷

FCM clustering segmentation algorithm based on pixel mutual relationship
Zhou Youhang,Liu Hanjiang,Zhao Hanyun and Zhao Yu.FCM clustering segmentation algorithm based on pixel mutual relationship[J].Chinese Journal of Scientific Instrument,2019,40(9):124-131.
Authors:Zhou Youhang  Liu Hanjiang  Zhao Hanyun and Zhao Yu
Affiliation:School of Mechanical Engineering, Xiangtan University, Xiangtan 411105, China,School of Mechanical Engineering, Xiangtan University, Xiangtan 411105, China,School of Mechanical Engineering, Xiangtan University, Xiangtan 411105, China and School of Mechanical Engineering, Xiangtan University, Xiangtan 411105, China
Abstract:Aiming at the problems that traditional fuzzy C means (FCM) algorithm does not consider the mutual relationship among pixels and requires to obtain the initial cluster center when dealing with image segmentation, the paper proposes a FCM clustering segmentation algorithm considering the relationship among pixels. Firstly, the algorithm adopts the principle of data field, uses the mutual relationship among the pixels to calculate the potential values of the pixels and form the image data field. Then, the initial cluster center of the FCM algorithm is determined with the image data field potential center. Finally, based on the image data field, the FCM algorithm is used to realize the clustering segmentation of the target image. In order to verify the effectiveness of the algorithm, the artificial synthetic image and the workpiece surface defect image were used for experiments. The experiment results show that the algorithm has better segmentation effect. Meanwhile, for different noisy images with streaks, decarburization and hole defects, the segmentation accuracies are above 93%, and has a high mean structural similarity.
Keywords:image segmentation  data field  fuzzy C means  surface defect
本文献已被 CNKI 等数据库收录!
点击此处可从《仪器仪表学报》浏览原始摘要信息
点击此处可从《仪器仪表学报》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号