Use of Support Vector Machines for Defect Detection of Metal Bellows Welding

박민철; Young Tae Byun; Dong W. Kim

Journal of The Korea Society of Computer and Information

Abbr : JKSCI
2015, 20(1), pp.11-20
Publisher : The Korean Society Of Computer And Information
Research Area : Computer Science

박민철 ¹, Young Tae Byun ², Dong W. Kim ³

¹한국과학기술연구원
²한국과학기술연구원
³인하공업전문대학

ABSTRACT

Typically welded bellows are checked with human eye and microscope, and then go through leakagetest of gas. The proposed system alternates these heuristic techniques using support vector machines. Image procedures in the proposed method can cover the irregularity problem induced from human being. To get easy observation through microscope, 3D display system is also exploited. Experimental resultsfrom this automatic measurement show the welding detection is done within one tenth of permitted errorrange.
KEYWORDS

Metal Bellows Welding, Support Vector Machines, Defect Detection
REFERENCES (11)

[book] V. Vapnik / 1995 / The Nature of Statistical Learning Theory / John Wiley

[journal] W. Wang / 2004 / A heuristic training for support vector regression / Neurocomputing 61 : 259~275

[journal] M. Matsumoto / 2014 / Classification of silent speech usisng support vector machine and relevance vector machine / Applied Soft Comput 20 : 95~102

[journal] S. Ercan / 2014 / Patent value anaysis using support vector machines / Soft Comput 18 : 313~328

[journal] D.T. Lin / 2009 / Integrating a mixed-feature model and multiclass support vector machine for facial expression recognition / Integr Comput-Aid E 16 : 61~74

[web] / en.wikipedia.org/wiki/Metal_bellows / en.wikipedia.org/wiki/Metal_bellows

[report] S. Gunn / 1998 / Support vector machines for classification and regression, ISIS Technical Report / Image Speech & Intelligent Systems Group, University of Southampton

[journal] D. Casali / 2006 / Associative Memory Design Using Support Vector Machines / IEEE Trans. Neural Networks 17(5) : 1165~1174

[journal] 김동원 / 2009 / Use of Support Vector Regression in Stable Trajectory Generation for Walking Humanoid Robots / ETRI Journal / 한국전자통신연구원 31(5) : 565~575

[web] / http://svmlight.joachims.org/ / http://svmlight.joachims.org/

[web] / http://en.wikipedia.org/wiki/3D_display / http://en.wikipedia.org/wiki/3D_display
KCI Citation (0)

KJC Korea
Journal Central

Statistics

Tools