Abstract
In face recognition, a simple classifier such as k -NN is frequently used. For a robust system, it is common to construct the multiclass classifier by combining the outputs of several binary ones. The two basic schemes for this purpose are known as one-per-class (OPC) and pairwise coupling (PWC). The performance of decomposition methods depends on accuracy of base dichotomizers. Support vector machine is suitable for this purpose. In this paper, we give the strength and weakness of two representative decomposition methods, OPC and PWC. We also introduce a new method combining OPC and PWC with rejection based on the analysis of OPC and PWC using SVM as base classifiers. The experimental results on the ORL face database show that our proposed method can reduce the error rate on the real dataset.
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
Vapnik, V. N.: Statistical Learning Theory. John Wiley & Sons, New York (1998)
Phillips, P. J.: Support vector machines applied to face recognition. Advanced in Neural Information Processing System II, MIT Press (1998) 803–809
G. Guo, S. Z. Li, and K. L. Chan: Support vector machines for face recognition. Image and Vision Computing, Vol. 19 (2001) 631–638
Heisele, B., Ho P., Poggio T.: Face recognition with support vector machines: Global versus Component-based Approach. Proc. of IEEE International Conference on Computer Vision (2001) 688–694
Hastie T., Tibshirani R.: Classification by Pairwise Coupling. Advances in Neural Information Processing Systems, Vol. 10, MIT Press (1998)
Dietterich T. G., Bakiri G.: Solving Multiclass Learning Problems via Error-Correcting Output Codes. Journal of Artificial Intelligence Research, Vol. 2 (1995) 263–286
Hansen L., Salamon P.: Neural network ensembles. IEEE Trans. on PAMI, Vol. 12, No. 10 (1990) 993–1001
Allwein E. L., Schapire R. E., Singer Y.: Reducing Multiclass to Binary: A Unifying Approach for Margin Classifiers. Proc. of International Conference on Machine Learning (2000) 9–16
Valentini G.: Upper bounds on the training error of ECOC-SVM ensembles. Technical Report TR-00-17, DISI-Dipartimento di Informatica Scienze dell’ Informazione (2000)
Masulli F., Valentini G.: Comparing Decomposition Methods for Classification. Proc. of International Conference on Knowledge-based Intelligent Engineering Systems & Allied Technologies, Vol. 2 (2000) 788–791
Klautau A., Jevtic N., Orlisky A.: Combined Binary Classifiers with Applications to Speech Recognition. Proc. of International Conference on Spoken Language Processing (2002) 2469–2472
Alpaydm E., Mayoraz E.: Learning Error-Correcting Output Codes from Data. Proc. of International Conference on Artificial Neural Networks (1999)
Moreira M., Mayoraz E.: Improved Pairwise Coupling Classification with Correcting Classifiers. Proc. of European Conference on Machine Learning (1998) 160–171
Phillips P. J., Moon H., Rizvi S. A., Rauss P. J.: The FERET evaluation methodology for face-recognition algorithms. IEEE Trans. PAMI, Vol. 22, No. 10 (2000) 1090–1104
Almedia M. B.: SMOBR-A SMO program for training SVM. Univ. of Minas Gerais, Dept. of Electrical Engineering. http://www.cpdee.ufmg.br/~barros/
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ko, J., Byun, H. (2003). Combining SVM Classifiers for Multiclass Problem: Its Application to Face Recognition. In: Kittler, J., Nixon, M.S. (eds) Audio- and Video-Based Biometric Person Authentication. AVBPA 2003. Lecture Notes in Computer Science, vol 2688. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44887-X_63
Download citation
DOI: https://doi.org/10.1007/3-540-44887-X_63
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40302-9
Online ISBN: 978-3-540-44887-7
eBook Packages: Springer Book Archive