Abstract
We argue how we should deal with some pieces of information each of which is not so strong for person recognition. On the basis of Dempster-Shafer theory, we introduce: 1) a new method of assigning a basic probability to nodes on a decision tree that is a basic expression of our current psychological status when we recieve an evidence, and 2) an update rule to combine several evidences presented sequentially. In person identification, the effectioness of these approaches is confirmed.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Shafer, G.: A mathematical theory of evidences. Princeton University Press, Princeton (1976)
Matsuyama, T., Kurita, M.: Pattern Classification Based on Dempster-Shafer Probability Model -Belief Formation from Observation and Belief Integration Using Virtual Belief Space. IEICE, J76-D-II(4), 843–853 (1993)
Maeda, S., Okamoto, M., Kawahara, T., Minoh, M., Ikeno, K., Doushita, S.: Individual Identification by Integrating Facial Image, Walking Image and Vocal Feature. IEICE, J79-D-II(4), 600–607 (1996)
Sugie, Y., Kobayashi, T.: Media-Integrated Biometric Person Recognition Based on the Dempster-Shafer Theory. In: ICPR 2002, vol. 4, pp. 40381–40384 (2002)
Aoki, K., Kudo, M.: Decision Tree Using Class-Dependent Feature Subsets. In: Caelli, T.M., Amin, A., Duin, R.P.W., Kamel, M.S., de Ridder, D. (eds.) SPR 2002 and SSPR 2002. LNCS, vol. 2396, pp. 761–769. Springer, Heidelberg (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Yamada, M., Kudo, M. (2004). Combination of Weak Evidences by D-S Theory for Person Recognition. In: Negoita, M.G., Howlett, R.J., Jain, L.C. (eds) Knowledge-Based Intelligent Information and Engineering Systems. KES 2004. Lecture Notes in Computer Science(), vol 3213. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-30132-5_144
Download citation
DOI: https://doi.org/10.1007/978-3-540-30132-5_144
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-23318-3
Online ISBN: 978-3-540-30132-5
eBook Packages: Springer Book Archive