Abstract
In this paper, we propose a criterion for pairwise combination of information from different sensors in order to decide how a given pair of sensors is useful for different applications. This criterion is related to the principle of maximum information preservation. We present experimental results for the case of face images at different spectral bands, which allow for the in advance evaluation of the usefulness of different sensor combinations as well as the possibility for crossed-sensor recognition (matching of images acquired in different spectral bands). The criterion that we propose is a generalization of the Fisher score for the case of mutual information, which is measured as the ratio of the interclass information to the intraclass. The score we propose measures the behavior of a pair of sensors either when they are used in combination or when they are used to discriminate between classes. Based on Information Theory measurements, we conclude that the best spectral band combination always contains the thermal image, while the best combination for crossed-sensor recognition is VIS and NIR.
Similar content being viewed by others
References
Linsker R. Self-organization in a perceptual network. Computer. 1988;21(3):105–17.
Linsker R. From basic network principles to neural architecture (series): Proceedings of the National Academy of Sciences USA 83: 7508–12, 8390–94, 8779–83; 1986.
Fabregas J, Faundez-Zanuy M. “Biometric recognition performing in a bioinspired system” Cognitive computation. Springer. 2009;1(3):257–67.
Fabregas J, Faundez-Zanuy M. Biometric dispersion matcher. Elsevier Pattern recognit. 2008;41(11): 3412–3426.
Roure J, Faundez-Zanuy M. Face recognition with small and large size databases. 39th International Carnahan Conference on Security Technology ICCST’2005 Las Palmas de Gran Canaria. Spain. ISBN: 0-7803-9245-0, pp. 153–156. Oct 2005.
Color FERET. Facial Image Database, image group, information access division, ITL, National Institute of Standards and Technology. Oct 31, 2003. http://face.nist.gov/colorferet/.
Espinosa-Duró V, Faundez-Zanuy M, Mekyska J. Beyond cognitive signals. doi:10.1007/s12559-010-9035-6. Cognitive computation, Springer, 2010.
Shannon CE. A mathematical theory of communication. Bell Syst Techn J. 1948;27:379–423. 623–656.
Faundez-Zanuy M. Biometric security technology. IEEE Aerosp Electron Syst Mag. 2006;21(6):5–26.
Faundez-Zanuy M. Data fusion in biometrics. IEEE Aerosp Electron Syst Mag. 2005;20(1):34–8.
Fukunaga K. Statistical pattern recognition. 2nd ed. New York: Academic Press; 1990.
Cover TM, Thomas JA. Elements of information theory. New York: Wiley; 1991.
Haykin S. Neural networks: a comprehensive foundation. NJ: Prentice Hall; 1999.
Bressan M, Guillamet D, Vitrià J. Using an ICA representation of local color histograms for object recognition. Pattern Recognit. 2003;36(3):691–701.
Acknowledgments
This work has been supported by COST-2102, FEDER and MEC, TEC2009-14123-C04-04. We also want to acknowledge the COST OC08057 project for providing Jiri’s support. This project was also partially financed by TEC2009-14094-C04-01.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Espinosa-Duró, V., Faundez-Zanuy, M., Mekyska, J. et al. A Criterion for Analysis of Different Sensor Combinations with an Application to Face Biometrics. Cogn Comput 2, 135–141 (2010). https://doi.org/10.1007/s12559-010-9060-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12559-010-9060-5