文献类型：期刊文献

中文题名：X射线检测焊缝的图像处理与缺陷识别

英文题名：Research of Image Processing and Defect Recognition for Industrial Radiographic Weld Inspection

作者：张晓光[1];林家骏[1]

机构：[1]华东理工大学信息科学与工程学院

年份：2004

卷号：30

期号：2

起止页码：199

中文期刊名：华东理工大学学报（自然科学版）

外文期刊名：Journal of East China University of Science and Technology

收录：CSTPCD;;EI(收录号：2004268239454);Scopus;北大核心:【北大核心2000】；CSCD:【CSCD2011_2012】；

语种：中文

中文关键词：射线图像;焊缝检测;图像处理;缺陷识别

外文关键词：radiographic image; weld inspection; image analysis; defect recognition

摘要：根据射线检测焊缝图像的特点,设计了图像去噪、增强的算法;针对焊缝缺陷对比度差、光照不均、纹理较多等不利因素,在去除焊缝背景情况下,设计了动态划分焊缝区域算法,利用局域阈值法分割提取出对比度不均的缺陷;通过对焊缝缺陷特征分析,选取缺陷识别的特征参数;建立了用于焊缝缺陷识别的模糊神经网络模型。试验结果表明,图像预处理和缺陷提取是成功的,提出的识别算法能够提高介于模糊边界模式分类时的识别率,对焊缝缺陷识别的效果优于分类识别法。
The algorithm of image noise reduction and enhancement is designed according to the characteristics of weld radiographic image, in the case of various unfavorable factors such as bad contrast ratio of weld defects, illumination asymmetry and many textures; the algorithm for extracting the weld (defect) is designed, based on edge inspection under weld background condition. Through analyzing weld (defect) features, defect feature parameters are selected, the fuzzy neural network model used to recognize weld (defects) is developed, and the methodology of constructing membership are introduced. From experiments, it was successful for image preprocessing and defect extraction. The recognition algorithm could raise the recognition ratio based on fuzzy boundary pattern classification, which is better than classification recognition method for weld defect recognition.