文献类型：期刊文献

中文题名：基于形态学的焊缝X射线图像缺陷检测

英文题名：Defect Recognition of Weld X-Ray Image Based on Morphology

作者：王勇[1];郭慧[1]

机构：[1]华东理工大学机械与动力工程学院,上海200237

年份：2013

卷号：39

期号：4

起止页码：460

中文期刊名：东华大学学报（自然科学版）

外文期刊名：Journal of Donghua University(Natural Science)

收录：CSTPCD;;北大核心:【北大核心2011】；CSCD:【CSCD2013_2014】；

语种：中文

中文关键词：焊缝;缺陷位置;形态学;缺陷检测;轮廓提取

外文关键词：weld; defect location; morphology; defect detection; contour extraction

摘要：通过对焊缝X射线图像进行垂直扫描,提取扫描线的线灰度曲线,提出了焊缝缺陷位置的检测算法.应用形态学滤波和分水岭变换对缺陷轮廓进行提取,实现了焊缝X射线图像缺陷的检测.对图像的实测结果表明,该方法能有效地对焊缝缺陷位置进行检测.
By scanning the vertical weld X-ray image, the gray curve of scan line was extracted, and a method for detecting the defect location was proposed. The morphological filtering and the watershed transformation method were used to extract the defect profile and to recognize the weld defects of X-ray image. The results of image detection show that this method can effectively detect the position of the weld defects.