Abstract
Biometric person authentication is a secure and user-friendly way of identifying persons in a variety of everyday applications. In order to achieve high recognition rates, we propose an audio-visual person recognition system based on voice, lip motion and still image. The combination of these three data sources (called sensor fusion) may be performed in several ways. We present a method for a sensor normalization based on statistical properties which we call sensor calibration. The final fusion simplifies to a multiplication or addition of the outputs of each sensor. This approach is evaluated on a large database of 170 people with a total of 6315 recordings which were recorded in at least two sessions per person.
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
U. Dieckmann, P. Plankensteiner, R. Schamburger, B. Fröba, and S. Meller, “Sesam: A biometric person identification system using sensor fusion,” in AVBPA97, pp. 301–310, March 1997.
K. R. Castelman, Digital Image Processing. New Jersey Prentice Hall, 1996.
U. Dieckmann, P. Plankensteiner, and T. Wagner, “Multisensory pattern analysis for person identification with synergetic computers”, in International Workshop on Automated Face-and Gesture-Recognition, pp. 368–371, 1995.
R. W. Frischholz, F. Böbel, and K. P. Spinnler, “Face recognition with the synergetic computer,” in Proceedings of the First International Conference on Applied Synergetic and Synergetic Engineering, (Erlangen), pp. 100–106, 1994.
B. Horn and B. Schunk, “Determining optical flow,” Artificial Intelligence, vol. 17, pp. 185, 1981.
E. G. Schukat-Talamazzini, Automatische Spracherkennung. BaunschweigWiesbaden: Vieweg, 1995.
Y. Linde, A. Buzo, and R. M. Grey, “An algorithm for vector quantizer design,” IEEE Transactions on Communication, pp. 84–95, January 1980.
S. Ben-Yacoub, Y. Abdeljaoued, and E. Mayoraz, “Fusion of face and speech data for person identity verification,” IDIAP-RR 03, IDIAP, 1999.
L. A. Klein, Sensor and Data Fusion Concepts and Applications. SPIE Press, 1999.
J. Kittler, Y.P. Li, J. Matas, and M. U. Ramos Sanchez, “Combining evidence in multimodal person identity recognition systems,” in AVBPA97, pp. 327–334, March 1997.
T. Choudhury, B. Clarkson, T. Jebara, and A. Pentland, “Multimodal person recognition using unconstrained audio and video,” in AVBPA99, pp. 176–181, March 1999.
A. Jain, L. Hong, and Y. Kulkarni, “A multimodal biometric system using fingerprint, face and speech,” in AVBPA99, pp. 182–187, March 1999.
R. Inguva and G. Garrison, “Fusion of lwir sensor data by bayesian methods,” in Sensor Fusion: Architectures, Algorithms, and Applications II, (Orlando, Florida), pp. 161–172, SPIE, April 1998.
Y. Abdeljaoued, “Fusion of person authentication probabilities by bayesian statistics,” in AVBPA99, pp. 172–175, March 1999.
J. Kittler, M. Hatef, R. P. Duin, and J. Matas, “On combining classifiers,” IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2000 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Fröba, B., Rothe, C., Küblbeck, C. (2000). Statistical Sensor Calibration for Fusion of Different Classifiers in a Biometric Person Recognition Framework. In: Multiple Classifier Systems. MCS 2000. Lecture Notes in Computer Science, vol 1857. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45014-9_35
Download citation
DOI: https://doi.org/10.1007/3-540-45014-9_35
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-67704-8
Online ISBN: 978-3-540-45014-6
eBook Packages: Springer Book Archive