Abstract
We present a framework for automatic inspection of welding seams based on specular reflections. To this end, we make use of a feature set – called specularity features (SPECs) – that describes statistical properties of specular reflections. For the classification we use a one-class support-vector approach. We show that the SPECs significantly outperform other approaches since they capture more complex characteristics and dependencies of shape and geometry. We obtain an error rate of 3.8%, which corresponds to the level of human performance.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Ong, T., Samad, Z., Ratnam, M.: Solder joint inspection with multi-angle imaging and an artificial neural network. The Int. Journal of Advanced Manufacturing Technology 38, 455–462 (2008)
Kim, J., Cho, H.: Neural network-based inspection of solder joints using a circular illumination. Image and Vision Computing 13, 479–490 (1995)
Chiu, S., Perng, M.: Reflection-area-based feature descriptor for solder joint inspection. Machine Vision and Applications 18, 95–106 (2007)
Ko, K., Cho, H.: Solder joints inspection using a neural network and fuzzy rule-based classification method. IEEE Transactions on Electronics Packaging Manufacturing 23, 93–103 (2000)
Poechmueller, W., Glesner, M., Listl, L., Mengel, P.: Automatic classification of solder joint images. In: Proc. of the Int. Joint Conf. on Neural Networks, vol. 2, pp. 933–940. IEEE Computer Society Press, Los Alamitos (1991)
Driels, M., Lee, C.: Feature selection for automatic visual inspection of solder joints. The Int. Journal of Advanced Manufacturing Technology 3, 3–32 (1988)
Cortes, C., Vapnik, V.: Support-vector networks. Machine Learning 20, 273–297 (1995)
Boser, B., Guyon, I., Vapnik, V.: A training algorithm for optimal margin classifiers. In: Haussler, D. (ed.) Proc. of the 5th Annual ACM Workshop on Computational Learning Theory, pp. 144–152. ACM Press, New York (1992)
Vapnik, V.: The Nature of Statistical Learning Theory. Springer, New York (1995)
Timm, F., Klement, S., Martinetz, T., Barth, E.: Welding inspection using novel specularity features and a one-class svm. In: Proc. of the Int. Conference on Imaging Theory and Applications, vol. 1, pp. 146–153. INSTICC (2009)
Schölkopf, B., Platt, J.C., Shawe-Taylor, J., Smola, A.J., Williamson, R.C.: Estimating the support of a high-dimensional distribution. Neural Computation 13, 1443–1471 (2001)
Tax, D.M.J., Duin, R.P.W.: Support vector data description. Machine Learning 54, 45–66 (2004)
Labusch, K., Timm, F., Martinetz, T.: Simple incremental one-class support vector classification. In: Rigoll, G. (ed.) DAGM 2008. LNCS, vol. 5096, pp. 21–30. Springer, Heidelberg (2008)
Chen, Y.Q., Nixon, M.S., Thomas, D.W.: Statistical geometrical features for texture classification. Pattern Recognition 28, 537–552 (1995)
Walker, R., Jackway, P.T.: Statistical geometric features: Extensions for cytological texture analysis. In: Proc. of the 13th Int. Conf. on Pattern Recognition, pp. 790–794. IEEE Computer Society Press, Los Alamitos (1996)
Russ, J.C.: The Image Processing Handbook. CRC Press, Boca Raton (2007)
Timm, F., Klement, S., Martinetz, T.: Fast model selection for maxminover-based training of support vector machines. In: Proc. of the 19th Int. Conf. on Pattern Recognition, Florida, USA. IEEE Computer Society Press, Los Alamitos (2008)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Timm, F., Martinetz, T., Barth, E. (2010). Optical Inspection of Welding Seams. In: Ranchordas, A., Pereira, J.M., Araújo, H.J., Tavares, J.M.R.S. (eds) Computer Vision, Imaging and Computer Graphics. Theory and Applications. VISIGRAPP 2009. Communications in Computer and Information Science, vol 68. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-11840-1_20
Download citation
DOI: https://doi.org/10.1007/978-3-642-11840-1_20
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-11839-5
Online ISBN: 978-3-642-11840-1
eBook Packages: Computer ScienceComputer Science (R0)