首页 | 本学科首页   官方微博 | 高级检索  
     

焊接缺陷的X射线自动检测图像处理
引用本文:陆艺丹,张薇.焊接缺陷的X射线自动检测图像处理[J].光学仪器,2018,40(4):26-32.
作者姓名:陆艺丹  张薇
作者单位:上海理工大学光电信息与计算机工程学院;上海理工大学上海市现代光学系统重点实验室;上海理工大学教育部光学仪器与系统工程研究中心
基金项目:国家重点研发计划资助课题(2016YFF0101402);国家自然科学基金项目(61205015、61505107)
摘    要:X射线无损检测对于焊接结构件的质量保证具有重要意义。使用Image J图像处理软件和Java语言开发插件,对焊接点中气孔分布以及面积等缺陷参数进行自动检测并对获得的图像进行分析处理。提出利用区域标记法分割出有效分析区域,先去除无效区域后再对感兴趣区域进行气孔提取,相较于传统的全局图像差分法,可以减少背景对缺陷检测的影响,降低误判率。设计出的检测方法能够对特定图像进行批量分析,可以减少检测的时间。

关 键 词:X射线  焊接缺陷  气孔  区域标记  图像处理
收稿时间:2018/2/27 0:00:00

Image processing of X-ray automatic inspection for welding defects
LU Yidan and ZHANG Wei.Image processing of X-ray automatic inspection for welding defects[J].Optical Instruments,2018,40(4):26-32.
Authors:LU Yidan and ZHANG Wei
Affiliation:School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China and School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China;Shanghai Key Laboratory of Modern Optical System, University of Shanghai for Science and Technology, Shanghai 200093, China;Engineering Research Center of Optical Instruments and Systems(MOE), University of Shanghai for Science and Technology, Shanghai 200093, China
Abstract:The radiographic testing of non-destructive inspection is quite significant for the quality of welding construction.This paper uses image processing tool Image J to process X-ray images and develops plugin based on Java which is used to detect the distribution of voids in the solder joints and other parameters like area.In this paper,we describe a method based on segmenting effective analysis region with component labeling.Firstly,the invalid area is removed.Then,voids area is withdrawn in region of interest.In contrast to the traditional method based on global image,the proposed method decreases the influence of the background and reduces miscalculations.The plugin developed by Java can analyze batch images and reduce time.
Keywords:X-ray  welding defects  voids  component labeling  image processing
本文献已被 CNKI 等数据库收录!
点击此处可从《光学仪器》浏览原始摘要信息
点击此处可从《光学仪器》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