文献类型：会议论文

英文题名：Research on the solder joint image segmentation based on the improved spatial fuzzy C means algorithm

作者：Li, Meng-Xiao[1]; Wan, Yong-Jing[1]

机构：[1] School of Information Science and Engineering, East China University of Science and Technology, Shanghai, China

会议论文集：2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery, ICNC-FSKD 2016

会议日期：August 13, 2016 - August 15, 2016

会议地点：Changsha, China

语种：英文

外文关键词：Copying - Defects - Fuzzy clustering - Clustering algorithms - Image enhancement - Polychlorinated biphenyls

摘要：According to the characteristics of the PCB solder joint image, we put forward the membership degree's calculation formula of the spatial fuzzy C means(SFCM) algorithm which uses the visual information of the Lab value and the spatial information in the Lab space. The segmentation of the solder joint image and the step of marking the defects are introduced in detail. It is proposed that the solder joint defect degree is calculated by the image segmentation results of the solder joint, and the identification and marking of the defects are carried out according to the value of the defect degree. Experimental results show that the improved algorithm can not only obtain satisfactory image segmentation results, but also obtain more accurate recognition results in the application of the solder joint defect recognition. ? 2016 IEEE.