Rejecting Foreign Elements in Pattern Recognition Problem - Reinforced Training of Rejection Level

Wladyslaw Homenda, Agnieszka Jastrzebska, Witold Pedrycz

Abstract

Standard assumption of pattern recognition problem is that processed elements belong to recognized classes. However, in practice, we are often faced with elements presented to recognizers, which do not belong to such classes. For instance, paper-to-computer recognition technologies (e.g. character or music recognition technologies, both printed and handwritten) must cope with garbage elements produced at segmentation level. In this paper we distinguish between elements of desired classes and other ones. We call them native and foreign elements, respectively. The assumption that we have only native elements results in incorrect inclusion of foreign ones into desired classes. Since foreign elements are usually not known at the stage of recognizer construction, standard classification methods fail to eliminate them. In this paper we study construction of recognizers based on support vector machines and aimed on coping with foreign elements. Several tests are performed on real-world data.

References

  1. Chang, C. C. and Lin, C. J. (2011). LIBSVM: A library for support vector machines. ACM Transactions on Intelligent Systems and Technology, 2(3):1-27.
  2. Cortes, C. and Vapnik, V. (1995). Support-vector networks. Machine Learning, 20(3):273-297.
  3. Homenda, W., Luckner, M., and Pedrycz, W. (2013). Classification with rejection: concepts and formal evaluations. In Proc. 8th Int. Conf. on KICSS, pages 161- 172.
  4. Homenda, W., Luckner, M., and Pedrycz, W. (2014). Classification with rejection based on various SVM techniques. In Proceedings of the WCCI 2014 IEEE World Congress on Computational Intelligence, pages 3480- 3487.
  5. LeCun, Y., Cortes, C., and Burges, C. (1996). mnist database of handwritten diggits. http://yann.lecun.com/exdb/mnist/.
  6. Ng, A. Y., Jordan, M. I., and Weiss, Y. (2001). On spectral clustering: Analysis and an algorithm. In Advances in Neural Information Processing Systems, volume 14, pages 849-856.
  7. Pedregosa, F. et al. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12:2825-2830.
  8. Pillai, I., Fumera, G., and Roli, F. (2011). A classification approach with a reject option for multi-label problems. In Proc. 16th Int. Conf. on Image Analysis and Processing, volume 6978, pages 98-107.
  9. Schölkopf, B., Smola, A. J., Williamson, R. C., and Bartlett, P. L. (2000). New support vector algorithms. Neural computation, 12(5):1207-1245.
  10. Schölkopf, B., Williamson, R. C., Smola, A. J., ShaweTaylor, J., and Platt, J. C. (1999). Support vector method for novelty detection. In Proc. Advances in Neural Information Processing Systems, volume 12, pages 582-588.
  11. Shi, J. and Malik, J. (2000). Normalized Cuts and Image Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(8):888-905.
  12. Stefano, C., Sansone, C., and Vento, M. (2000). To reject or not to reject: that is the question - an answer in case of neural classifiers. IEEE Transactions on Systems, Man, and Cybernetics, Part C, 30(1):84-94.
  13. von Luxburg, U. (2007). A tutorial on spectral clustering. Statistics and Computing, 17(4):395-416.
  14. Weber, D.M.; Du Preez, J. (1993). A comparison between hidden markov models and vector quantization for speech independent speaker recognition. In Proc. South African Symposium on Comm. and Signal Processing, pages 139-144.
  15. Yu, S. X. and Shi, J. (2003). Multiclass spectral clustering. In Proc. 9th Int. Conf. on Comp. Vision, volume 1, pages 313-319.
  16. Zhang, B. (2011). Breast cancer diagnosis from biopsy images by serial fusion of random subspace ensembles. In Proc. 4th Int. Conf. on BMEI, pages 180-186.
Download


Paper Citation


in Harvard Style

Homenda W., Jastrzebska A. and Pedrycz W. (2015). Rejecting Foreign Elements in Pattern Recognition Problem - Reinforced Training of Rejection Level . In Proceedings of the International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, ISBN 978-989-758-074-1, pages 90-99. DOI: 10.5220/0005207900900099


in Bibtex Style

@conference{icaart15,
author={Wladyslaw Homenda and Agnieszka Jastrzebska and Witold Pedrycz},
title={Rejecting Foreign Elements in Pattern Recognition Problem - Reinforced Training of Rejection Level},
booktitle={Proceedings of the International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,},
year={2015},
pages={90-99},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005207900900099},
isbn={978-989-758-074-1},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,
TI - Rejecting Foreign Elements in Pattern Recognition Problem - Reinforced Training of Rejection Level
SN - 978-989-758-074-1
AU - Homenda W.
AU - Jastrzebska A.
AU - Pedrycz W.
PY - 2015
SP - 90
EP - 99
DO - 10.5220/0005207900900099