全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

基于磁光图像的飞机铆钉缺陷识别

DOI: 10.11834/jig.20071223

Keywords: 磁光图像,星形矢量,支持向量机

Full-Text   Cite this paper   Add to My Lib

Abstract:

针对飞机铆钉磁光图像的识别问题,提出了一种基于模糊支持向量机的裂纹有无和裂纹方向自动识别的新方法。该方法首先对铆钉磁光图像进行预处理得到铆钉二值化图像;然后采用阈值法求取铆钉中心;最后将由铆钉中心发出的星形射线矢量作为特征,采用模糊支持向量机方法对铆钉有无裂纹和裂纹方向进行分类。其中,支持向量机的核宽及惩罚常数采用网格法进行选取,并结合模糊隶属度函数解决多类分类问题中存在的错分和拒分现象。实验结果表明,使用训练获得的支持向量机分类器识别裂纹缺陷取得了很好的效果,能够满足自动检测的高实时性要求。

References

[1]  Thome D K,Fitzpatrick G L,Skaugset R L,et al.Aircraft corrosion and crack inspection using advanced magneto-optic imaging technology[A].In:Proceedings of SPIE-The International Society for Optical Engineering[C],Scottsdale,AZ,USA,1996,2945:365 ~373.
[2]  Park U,Fan Y,Udpa L,et al.Automated rivet inspection for aging aircraft with magneto-optic imager[A].In:Proceedings of the 10th International Workshop on Electromagnetic Nondestructive Evaluation[C],East Lansing,Michigan,USA,2004.
[3]  Simms S.MOI:magneto-optic/eddy current imaging[J].Materials Evaluation,1993,50 (5):529 ~ 536.
[4]  Deng Nai-yang,Tian Ying-jie.New Method in Data Mining-Support Vector Machine[M].Beijing:Science Press,2004:186 ~ 196.[邓乃扬,田英杰.数据挖掘中的新方法--支持向量机[M].北京:科学出版社,2004:186~196.]
[5]  Chapelle O,Vapnik V,Bousquet O,et al.Choosing multiple parameters for support vector machine[J].Machine Learning,2002,46(1):131 ~ 159.
[6]  Vapnik V,Chapelle O.Bounds on error expectation for support vector machine[J].Neural Computation,2000,12(9):2013 ~ 2036.
[7]  Fitzpatrick G L,Thome D K,Skaugset R L,et al.Magneto-optic/eddy current imaging of aging aircraft:a new NDI technique[J].Materials Evaluation,1993,51 (12):1402 ~ 1407.
[8]  Ramuhalli P,Slade J,Park U,et al.Modeling and signal processing of magneto-optic images for aviation applications[A].In:Proceedings of ISSS-SPIE International Conference on Smart Materials Structures and Systems[C],Bangalore,India,2002,5062:248 ~255.
[9]  Park U,Udpa L,George C.Motion-based filtering of magneto-optic imagers[J].Image and Vision Computing,2004,22 (3):243 ~249.
[10]  Lemistre M,Decitre J M.Corrosion and cracks detection in metallic structures by magneto optic image[A].In:Proceedings of International Conference on Quality Control by Artificial Vision[C],Le Creusot,France,2001:65 ~ 70.
[11]  Wang Peng,Zhu Xiao-yan.Model selection of SVM with RBF kernel and its application[J].Computer Engineering and Applications,2003,39(24):72~73[王鹏,朱小燕.基于RBF核的SVM的模型选择及其应用[J].计算机工程与应用,2003,39(24):72~73.]

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133