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。
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 Xray 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on segmenting effective analysis region with component labeling.Firstly,the invalid area is removed.Then,voids area is withdrawn in region of interest.In contrast to the traditional method based on global image,the proposed method decreases the influence of the background and reduces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.
作者
陆艺丹
张薇
LU Yidan;ZHANG Wei(School of OpticabElectrical 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)
出处
《光学仪器》
2018年第4期26-32,共7页
Optical Instruments
基金
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)
关键词
X射线
焊接缺陷
气孔
区域标记
图像处理
X-ray
welding defects
voids
component labeling
image processing
