Detection of Weld Slim Line Defects in X-Ray Digitized Film Images
摘 要
焊缝X射线数字化图像中像素宽度不超过3个像素的细长线缺陷, 其对比度低, 常有间断, 常规的X射线焊缝缺陷检出算法难以有效检出。针对此类缺陷, 提出了在滤波降噪的基础上, 采用逐列自适应阈值法对图像中细长线缺陷进行初步分割, 然后应用改进的局部霍夫变换剔除初步分割结果中的大量噪点, 准确分割出细长线缺陷。试验结果表明, 所提出的方法能够适应不同灰度范围的X射线图像、克服噪声及缺陷间断的影响, 有效检测出低对比度细长线缺陷。
Abstract
The slim line defect whose average width is not more than three pixels in X-ray weld images is usually weak and interrupted. Normal X-ray defects detection algorithm can not detect it effectively. A new method is proposed to detect this kind of defects. After filter the original X-ray image to reduce the noise, the self-adaptive threshold value is adopted line by line to segment the slim line defects in the image preliminarily, and the improved partial Hough Transform is used to eliminate the noise and segment the line defect. The experimental results show that the proposed method can adapt to X-ray digitized images of different grey range and avoid the influence of much noise and interruption, and is effective to detect the low-contrast slim line defects.
中图分类号 TG115.28
所属栏目 科研成果与学术交流
基金项目 中国焊接学会创新思路预研奖学金资助项目; 教育部高等学校博士学科点专项科研基金资助项目(20090002110080)
收稿日期 2009/9/4
修改稿日期
网络出版日期
作者单位点击查看
备注邵家鑫(1983-), 男, 博士研究生, 研究方向为无损检测与数字图像处理技术。
引用该论文: SHAO Jia-Xin,DU Dong,WANG Li,WANG Cheng,GAO Zhi-Ling. Detection of Weld Slim Line Defects in X-Ray Digitized Film Images[J]. Nondestructive Testing, 2010, 32(12): 921~925
邵家鑫,都 东,王 力,王 晨,高志凌. 焊缝X射线胶片数字化图像低对比度细长线缺陷的检测[J]. 无损检测, 2010, 32(12): 921~925
共有人对该论文发表了看法,其中:
人认为该论文很差
人认为该论文较差
人认为该论文一般
人认为该论文较好
人认为该论文很好
参考文献
【1】周正干, 腾升化, 江巍, 等.焊缝X射线检测及其结果的评判方法综述[J].焊接学报, 2002, 23(3): 85-88.
【2】Yan Wang, Yi Sun, Peng Lv. Detection of line weld defects based on multiple threshold and support vector machine[J]. NDT&E International, 2008, 41: 517-524
【3】张晓光, 高顶.射线检测焊接缺陷的提取和自动识别[J].北京: 国防工业出版社, 2004: 44.
【4】侯润石, 邵家鑫, 王力.焊缝缺陷X射线实时自动检测系统的图像处理[J].无损检测, 2009, 31(2): 99-101.
【5】Rafel C. Gonzalez, Richard E. Woods, Steven L. Eddins.数字图像处理(第二版)[M].北京: 电子工业出版社, 2005: 476-479.
【6】Wayne Niblack, Dragutin Petkovic. On improving the accuracy of the Hough transform: theory, simulations, and experiments[J]. Computer Vision and Pattern Recognition, 1988(6): 574-579.
【7】Ming Zhan. On the discretization of parameter domain in hough transform[J]. Pattern Recognition, 1996, 8(2): 527-531.
【8】Linfeng Guo, Opas Chutatape. Influence of discretization in image space on Hough transform[J]. Pattern Recognition, 1999, 4(32): 635-644.
【2】Yan Wang, Yi Sun, Peng Lv. Detection of line weld defects based on multiple threshold and support vector machine[J]. NDT&E International, 2008, 41: 517-524
【3】张晓光, 高顶.射线检测焊接缺陷的提取和自动识别[J].北京: 国防工业出版社, 2004: 44.
【4】侯润石, 邵家鑫, 王力.焊缝缺陷X射线实时自动检测系统的图像处理[J].无损检测, 2009, 31(2): 99-101.
【5】Rafel C. Gonzalez, Richard E. Woods, Steven L. Eddins.数字图像处理(第二版)[M].北京: 电子工业出版社, 2005: 476-479.
【6】Wayne Niblack, Dragutin Petkovic. On improving the accuracy of the Hough transform: theory, simulations, and experiments[J]. Computer Vision and Pattern Recognition, 1988(6): 574-579.
【7】Ming Zhan. On the discretization of parameter domain in hough transform[J]. Pattern Recognition, 1996, 8(2): 527-531.
【8】Linfeng Guo, Opas Chutatape. Influence of discretization in image space on Hough transform[J]. Pattern Recognition, 1999, 4(32): 635-644.
相关信息