PCA-Based Defect Enhancement and Segmentation for X-Ray Images of Welds
摘 要
为提高X射线图像缺陷自动识别的能力与图像分割的效果, 提出了一种基于主成分分析法的X射线焊缝缺陷图像增强与分割算法。该算法首先通过计算图像的协方差矩阵特征值与其对应的特征向量, 并根据特征向量分布, 选择感兴趣区域即图像中的焊缝部分, 从而减少图像处理的计算量; 其次通过分析特征值累计百分比和试验结果, 筛选出最佳的特征向量, 对图像进行基于主成分的重构; 最后采用Otsu阈值分割法, 对重构后的图像进行分割。试验结果表明, 该算法在对比度低、噪声严重的X射线缺陷图像分割中有很好的应用效果。
Abstract
In order to improve the automated recognition and segmentation in X-ray image of weld defects, an algorithm of X-ray image enhancement and segmentation based principal component analysis (PCA) was proposed. Firstly, the eigenvalue and its corresponding eigenvector of the image covariance matrix were calculated, according to the distribution of eigenvalue, the region of interest (ROI), just as weld, was located, the calculation capacity was reduced; Secondly, through analyzing the eigenvalue cumulative percentage and experimental results, the optimum eigenvector was selected to reconstruct the image based on PCA; Finally, the Otsu thresholding segmentation approach was employed to segment the reconstructed image. The results showed that this algorithm was effective in segmenting the X-ray image which was low contrast and noise severely.
中图分类号 TG115.28
所属栏目 2010年远东无损检测论坛论文精选
基金项目 四川省国际科技合作与交流研究计划资助项目(2007H12-017)
收稿日期
修改稿日期
网络出版日期
作者单位点击查看
备注殷 鹰(1983-), 男, 博士, 主要从事无损检测图像处理技术研究及特种设备能效测试方面的工作。
引用该论文: YIN Ying,MAO Jian,SU Zhen-Wei. PCA-Based Defect Enhancement and Segmentation for X-Ray Images of Welds[J]. Nondestructive Testing, 2010, 32(9): 678~683
殷 鹰,毛 健,苏真伟. 基于主成分分析法的X射线焊缝缺陷图像增强与分割算法[J]. 无损检测, 2010, 32(9): 678~683
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】Yin Y, Tian G Y, Yin G F, et al. Defect identification and classification for digital X-ray images[J]. Applied Mechanics and Materials, 2008, (10/12): 543-547.
【2】Canny J F. A computetional approach to edge to detection[J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 1986, 8(6): 679-698.
【3】Huang Q M, Gao W, Cai W J. Three holding technique with adaptive window selection for uneren lighting image[J]. Pattern Recognition Letters, 2005, 26(6): 801-808.
【4】Alaknanda R S, Anand, Pradeep K. Flaw detection in radiographic weld images using morphologieal approuch[J]. NDT & E International, 2006(39): 29-33.
【5】Gao J B, Kwan P W, Gao Y. Robust multivate L1 principal component analysis and dimessionality reduction[J]. Neurocomputing, 2009, 72(4/6): 1242-1249.
【6】Chen T L, Tian G Y, Sophian A, et al. Feature extraction and selection for defect classification of pulsed eddy current NDT[J]. NDT & E International, 2008, 41(6): 467-476.
【7】Congde L, Chunmei Z, Taiyi Z, et al. Kernel based symmetrical principal component analysis for face classification[J]. Neuro computing, 2007, 70(4): 904-911.
【8】Mirapeix P B, García-Allende A, Cobo O M, et al. Real-time arc-welding defect detection and classification with principal component analysis and artificial neural networks[J]. NDT & E International, 2007, 40(4): 315-323.
【9】Kalyanasundaram P, Thirunavukkarasu S, Rao B P C, et al. Eigenvalue-based approach for enhancement of eddy current images of shallow defects[J]. Research in Nondestructive Evaluation, 2007, 18(1): 13-21.
【10】Otsu N. A threshold selection method from gray-level histograms[J]. IEEE Transactions on System, Man and Cybernetics, 1979, 9(1): 62-66.
【2】Canny J F. A computetional approach to edge to detection[J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 1986, 8(6): 679-698.
【3】Huang Q M, Gao W, Cai W J. Three holding technique with adaptive window selection for uneren lighting image[J]. Pattern Recognition Letters, 2005, 26(6): 801-808.
【4】Alaknanda R S, Anand, Pradeep K. Flaw detection in radiographic weld images using morphologieal approuch[J]. NDT & E International, 2006(39): 29-33.
【5】Gao J B, Kwan P W, Gao Y. Robust multivate L1 principal component analysis and dimessionality reduction[J]. Neurocomputing, 2009, 72(4/6): 1242-1249.
【6】Chen T L, Tian G Y, Sophian A, et al. Feature extraction and selection for defect classification of pulsed eddy current NDT[J]. NDT & E International, 2008, 41(6): 467-476.
【7】Congde L, Chunmei Z, Taiyi Z, et al. Kernel based symmetrical principal component analysis for face classification[J]. Neuro computing, 2007, 70(4): 904-911.
【8】Mirapeix P B, García-Allende A, Cobo O M, et al. Real-time arc-welding defect detection and classification with principal component analysis and artificial neural networks[J]. NDT & E International, 2007, 40(4): 315-323.
【9】Kalyanasundaram P, Thirunavukkarasu S, Rao B P C, et al. Eigenvalue-based approach for enhancement of eddy current images of shallow defects[J]. Research in Nondestructive Evaluation, 2007, 18(1): 13-21.
【10】Otsu N. A threshold selection method from gray-level histograms[J]. IEEE Transactions on System, Man and Cybernetics, 1979, 9(1): 62-66.
相关信息