Abstract
This paper investigates on the training of classifiers with highly imbalanced datasets for industrial quality control. The application is on-line process monitoring of laser brazing processes and only a limited amount of data of an imperfection class is available for training. Bayesian adaptation is used to derive a model of the imperfection class from a well sampled model of the class representing a high grade joint surface. For this application, we are able to show that with the sparse training data a performance comparable to a training with a balanced dataset is achievable and even a moderate increase of training data quickly yields a performance gain.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Grimm, A., Schmidt, M.: Possibilities for online process monitoring at laser brazing based on two dimensional detector systems. In: Proc. 28th Int. Congr. on Applications of Laser & Electro Optics, Orlando, FL, USA (2009)
Akbani, R., Kwek, S., Japkowicz, N.: Applying Support Vector Machines to Imbalanced Datasets. In: Boulicaut, J.-F., Esposito, F., Giannotti, F., Pedreschi, D. (eds.) ECML 2004. LNCS (LNAI), vol. 3201, pp. 39–50. Springer, Heidelberg (2004)
Bishop, C.: Pattern Recognition and Machine Learning. Inf. Science and Statistics. Springer (2006)
Donst, D., Abels, P., Ungers, M., Klocke, F., Kaierle, S.: On-line quality control system for laser brazing. In: Proc. of 28th Int. Congr. on Applications of Laser & Electro Optics, Orlando, FL, USA (2009)
Duda, R., Hart, P., Stork, D.: Pattern Classification, 2nd edn. Wiley-Interscience (2001)
Fecker, D., Maergner, V., Fingscheidt, T.: Online detection of imperfections in laser brazed joints. In: Proc. of the 12th IAPR Conference on Machine Vision Applications (MVA), Nara, Japan, pp. 223–227 (2011)
Fierrez-Aguilar, J., Garcia-Romero, D., Ortega-Garcia, J., Gonzalez-Rodriguez, J.: Bayesian adaptation for user-dependent multimodal biometric authentication. Pattern Recognition 38(8), 1317–1319 (2005)
Kaierle, S., Ungers, M., Franz, C., Mann, S., Abels, P.: Understanding the laser process. Laser Technik Journal 7(7), 49–52 (2010)
Kubat, M., Matwin, S.: Addressing the curse of imbalanced training sets: One-sided selection. In: Proc. of the Fourteenth International Conference on Machine Learning, pp. 179–186. Morgan Kaufmann, San Francisco (1997)
Reynolds, D., Quatieri, T., Dunn, R.: Speaker verification using adapted gaussian mixture models. Digital Signal Processing 10, 19–42 (2000)
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(7) (2001)
Shao, J., Yan, Y.: Review of techniques for on-line monitoring and inspection of laser welding. Journal of Physics: Conference Series 15, 101–107 (1995)
Tarassenko, L., Hayton, P., Cerneaz, N., Brady, M.: Novelty detection for the identification of masses in mammograms. In: Proc. of IEEE Conference on Artifical Neural Networks, Paris, France, pp. 442–447 (1995)
Tax, D.: One-class Classification. Phd thesis, Delft University of Technology, Delft (June 2001)
Tax, D., Duin, R.P.W.: Support vector data description. Machine Learning 54(1), 45–66 (2004)
Ungers, M., Fecker, D., Frank, S., Donst, D., Maergner, V., Abels, P., Kaierle, S.: In-situ quality monitoring during laser brazing. In: Proc. of Laser Assisted Net Shape Engineering 6, Erlangen, Germany, pp. 493–503 (2010)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Fecker, D., Märgner, V., Fingscheidt, T. (2012). Training of Classifiers for Quality Control of On-Line Laser Brazing Processes with Highly Imbalanced Datasets. In: Pinz, A., Pock, T., Bischof, H., Leberl, F. (eds) Pattern Recognition. DAGM/OAGM 2012. Lecture Notes in Computer Science, vol 7476. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-32717-9_37
Download citation
DOI: https://doi.org/10.1007/978-3-642-32717-9_37
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-32716-2
Online ISBN: 978-3-642-32717-9
eBook Packages: Computer ScienceComputer Science (R0)