基于自适应SVM决策树的焊缝缺陷类型识别
Welding Defects Classification Based on Adaptive SVM Decision Tree
摘 要
针对传统X射线焊缝缺陷检测方法普遍存在分类识别精度不高的问题, 提出了一种基于分离程度的自适应SVM决策树算法。首先对滤波后的X-Ray焊缝缺陷图像进行数学形态学重建, 然后根据分离程度, 每次将分离程度最大的缺陷类别首先分离出来, 构造自适应二叉树的SVM分类器, 从而达到了减小二叉树的累积误差, 得到了分类性能优良的的SVM决策树, 并用其对X-Ray焊缝缺陷图像进行分类识别。实验结果表明, 该算法取得了好的分类精度和识别效果。
支持向量机
分离程度
数学形态学
缺陷识别
Binary decision tree
Support vector machine
Degree of separation
Mathematical morphology
Welding defects classification
Abstract
An adaptive SVM(Support Vector Machines) based on binary tree using the degree of separation is proposed in this paper, aiming at the problem that it’s difficult for traditional detection methods to accurately identify the welding defects of X-Ray images. Firstly, mathematical morphological reconstruction is applied to the filtered X-Ray images of welding defects. It is proposed to separate category of defects with the largest degree of separation as a priority, and to construct adaptive SVM classifiers based on binary tree, thus decreasing the accumulated error. Finally, a SVM decision tree of good classification performance can be obtained, which is used to classify and identify the X-Ray images of welding defects, and it shows that the algorithm has made a good classification and recognition accuracy results.
中图分类号 TG115.28
所属栏目 科研成果与学术交流
基金项目 成都信息工程学院自然科学与技术发展基金资助(csrf200805)
收稿日期 2009/4/3
修改稿日期
网络出版日期
作者单位点击查看
备注李 坤(1987-), 男, 在读本科, 主要研究方向是光信息科学与技术。
引用该论文: LI Kun,WEN Bin,REN Qing-An,LUO Ai-Min. Welding Defects Classification Based on Adaptive SVM Decision Tree[J]. Nondestructive Testing, 2010, 32(3): 171～174
李 坤,文 斌,任清安,罗爱民. 基于自适应SVM决策树的焊缝缺陷类型识别[J]. 无损检测, 2010, 32(3): 171～174
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】中国机械工程学会.射线检测[M].北京: 机械工业出版社, 1997: 4-177.
【2】李德元, 邵成吉, 徐鲁宁.焊接缺陷自动检测中区分典型条形缺陷判据的建立[J].焊接技术, 1998, 28(1): 7-8.
【3】傅德胜.焊接缺陷计算机自动识别模式的研究[J].控制与决策, 1998, 13(增刊): 469-474.
【4】孙忠诚, 李鹤歧, 陶维道.焊缝X射线实时探伤数字图像处理方法研究[J].无损检测, 1992, 14(2): 37-40.
【5】Nacereddine Nafa, Drai Redouane. Weld defect extraction and classification inradiographic testing based artificial neural networks[C]// Proceeding of 15th WCNDT. Roma: [s.n.], 2000.
【6】Kapustin A E, Bardusova I I. Computer technologies and X-ray flaw detection of welds[C]// Proceeding of 15th WCNDT. Roma: [s.n.], 2000.
【7】Nacereddine N, Tridi M. Weld defects in industrial radiography based invariant attributes and neural networks[J]. Image and Signal Processing and Analysis, 2005(7): 15-17.
【8】Burges C. A tutorial on support vector machines for pattern recognition[J]. Data mining and knowledge discovery, 1998, 2(2): 121-167.
【9】Hus C W, Lin C J. Acompaison of methods for multi-class support vector machines[J]. IEEE Transaction on Neural Networks, 2002, 26(13): 414-425.
【10】Brown M P, Grundy W N, Lin D, et al. Knowledge-based analysis of microarray gene expression data by using support vector machines[C]// Proceeding of the National Academy of Sciences of the USA. USA: [s.n.], 2000: 262-267.
【11】孙林, 付静.基于二叉树的支持向量机旋转机械故障诊断方法[J].设计与研究, 2008, 35(3): 1-4.
【12】Trevor Hastie, Robert Tibshirani, Jerome Friedman. The Elements of Statistical Learning Data Mining, Inference, and Prediction[M]. American: Springer-verlab, 2004.263-272.
【13】冈萨雷斯.数字图像处理[M].北京: 电子工业出版社, 2003: 427-431.
【14】Crespo J, Serra J. Theoretical aspects of morphological filters by reconstruction[J]. Signal Processing, 1995, 47(2): 201-225.
【15】Katoh Y, O kumura T, Itoga K, et al Development of the automatic system for radiographic film interpretation[J]. NDT of Japan, 1992, 41(4): 186-195.
【16】张晓光, 林家骏.X射线检测焊缝的图像处理与缺陷识别[J].华东理工大学学报, 2004, 30(2): 199-202.
【2】李德元, 邵成吉, 徐鲁宁.焊接缺陷自动检测中区分典型条形缺陷判据的建立[J].焊接技术, 1998, 28(1): 7-8.
【3】傅德胜.焊接缺陷计算机自动识别模式的研究[J].控制与决策, 1998, 13(增刊): 469-474.
【4】孙忠诚, 李鹤歧, 陶维道.焊缝X射线实时探伤数字图像处理方法研究[J].无损检测, 1992, 14(2): 37-40.
【5】Nacereddine Nafa, Drai Redouane. Weld defect extraction and classification inradiographic testing based artificial neural networks[C]// Proceeding of 15th WCNDT. Roma: [s.n.], 2000.
【6】Kapustin A E, Bardusova I I. Computer technologies and X-ray flaw detection of welds[C]// Proceeding of 15th WCNDT. Roma: [s.n.], 2000.
【7】Nacereddine N, Tridi M. Weld defects in industrial radiography based invariant attributes and neural networks[J]. Image and Signal Processing and Analysis, 2005(7): 15-17.
【8】Burges C. A tutorial on support vector machines for pattern recognition[J]. Data mining and knowledge discovery, 1998, 2(2): 121-167.
【9】Hus C W, Lin C J. Acompaison of methods for multi-class support vector machines[J]. IEEE Transaction on Neural Networks, 2002, 26(13): 414-425.
【10】Brown M P, Grundy W N, Lin D, et al. Knowledge-based analysis of microarray gene expression data by using support vector machines[C]// Proceeding of the National Academy of Sciences of the USA. USA: [s.n.], 2000: 262-267.
【11】孙林, 付静.基于二叉树的支持向量机旋转机械故障诊断方法[J].设计与研究, 2008, 35(3): 1-4.
【12】Trevor Hastie, Robert Tibshirani, Jerome Friedman. The Elements of Statistical Learning Data Mining, Inference, and Prediction[M]. American: Springer-verlab, 2004.263-272.
【13】冈萨雷斯.数字图像处理[M].北京: 电子工业出版社, 2003: 427-431.
【14】Crespo J, Serra J. Theoretical aspects of morphological filters by reconstruction[J]. Signal Processing, 1995, 47(2): 201-225.
【15】Katoh Y, O kumura T, Itoga K, et al Development of the automatic system for radiographic film interpretation[J]. NDT of Japan, 1992, 41(4): 186-195.
【16】张晓光, 林家骏.X射线检测焊缝的图像处理与缺陷识别[J].华东理工大学学报, 2004, 30(2): 199-202.
相关信息
