Abstract
Recent research has established benefits of rank-level fusion in identification systems; however, these studies have not compared the advantages, if any, of rank-level fusion schemes over classical score-level fusion schemes. In the presence of low quality biometric data, the genuine match score is claimed to be low and expected to be an unreliable individual output. Conversely, the rank assigned to that genuine identity is believed to remain stable even when using low quality biometric data. However, to the best of our knowledge, there is not a deepen investigation on the stability of ranks. In this paper, we analyze changes of the rank assigned to the genuine identity in multi-modal scenarios when using actual low quality data. The performance is evaluated on a subset of the database Face and Ocular Challenge Series (FOCS) collection (the Good, Bad and Ugly database), composed of three frontal faces per subject for 407 subjects. Results show that a variant of the highest rank fusion scheme, which is robust to ties, performs better than the other non-learning based rank-level fusion methods explored in this work. However, experiments demonstrate that score-level fusion results in better identification accuracy than existing rank-level fusion schemes.
This is a preview of subscription content, log in via an institution to check access.
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
Monwar, M., Gavrilova, M.: Multimodal biometric system using rank-level fusion approach. IEEE Transactions on Systems, Man, and Cybernetics 39, 867–878 (2009)
Grother, P., Tabassi, E.: Performance of biometric quality measures. IEEE Transaction on Pattern Analysis and Machine Intelligence 29(4), 531–543 (2007)
Kittler, J., Li, Y.P., Matas, J., Sanchez, M.U.R.: Combining evidence in multimodal personal identity recognition systems. In: International Conference on Audio- and Video-based Biometric Person Authentication (1997)
Fierrez-Aguilar, J., Chen, Y., Ortega-Garcia, J., Jain, A.K.: Incorporating image quality in multi-algorithm fingerprint verification. In: International Conference on Biometrics (ICB), pp. 213–220 (January 2006)
Kittler, J., Poh, N.: Multibiometrics for identity authentication: Issues, benefits and challenges. In: IEEE Transaction on Pattern Analysis and Machine Intelligence (2009)
Jain, A., Nandakumar, K., Ross, A.: Score normalization in multimodal biometric systems. Pattern Recognition 38(12), 2270–2285 (2005)
Scheirer, W., Rocha, A., Micheals, R., Boult, T.: Robust fusion: Extreme value theory for recognition score normalization. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part III. LNCS, vol. 6313, pp. 481–495. Springer, Heidelberg (2010)
Ross, A., Jain, A.: Information fusion in biometrics. Pattern Recognition Letters 24, 2115–2125 (2003)
Tulyakov, S., Govindaraju, V.: Combining biometric scores in identification systems, pp. 1–34 (2006)
Monwar, M., Gavrilova, M.: Markov chain model for multimodal biometric rank fusion. In: Signal, Image and Video Processing, pp. 1863–1703 (2011)
Abaza, A., Ross, A.: Quality-based rank level fusion in biometrics. In: Third IEEE International Conference on Biometrics: Theory, Applications and Systems (September 2009)
Marasco, E., Ross, A., Sansone, C.: Predicting identification errors in a multibiometric system based on ranks and scores. In: Fourth IEEE International Conference on Biometrics: Theory, Applications and Systems (September 2010)
Labovitz, S.: The assignment of numbers to rank order categories. American Sociological Review 35(3), 515–524 (1970)
Bhat, D., Nayar, S.: Ordinal measures for image correspondence. IEEE Transactions on Pattern Analysis and Machine Intelligence 20(4), 415–423 (1998)
Friedman, M.: The use of ranks to avoid the assumption of normality implicit in the analysis of variance. Journal of the American Statistical Association 32(200), 675–701 (1937)
Wilcoxon, F.: Individual comparisons by ranking methods. Biometrics Bulletin 1(6), 80–83 (1945)
Nandakumar, K., Jain, A., Ross, A.: Score normalization in multimodal biometric systems. Pattern Recognition 38(12), 2270–2285 (2005)
Marasco, E., Abaza, A.: On the stability of ranks to low image quality in biometric identification systems. In: Petrosino, A. (ed.) ICIAP 2013, Part I. LNCS, vol. 8156, pp. 260–269. Springer, Heidelberg (2013)
Ross, A., Nandakumar, K., Jain, A.: Handbook of MultiBiometrics. Springer (2006)
Ho, T., Hull, J., Srihari, S.: Combination of decisions by multiple classifiers. In: Structured Document Image Analysis, pp. 188–202 (1992)
Moscato, F., Vittorini, V., Amato, F., Mazzeo, A., Mazzocca, N.: Solution workflows for model-based analysis of complex systems. IEEE Transactions on Automation Science and Engineering 9(1), 83–95 (2012)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer International Publishing Switzerland
About this paper
Cite this paper
Marasco, E., Abaza, A., Lugini, L., Cukic, B. (2013). Impact of Biometric Data Quality on Rank-Level Fusion Schemes. In: Aversa, R., Kołodziej, J., Zhang, J., Amato, F., Fortino, G. (eds) Algorithms and Architectures for Parallel Processing. ICA3PP 2013. Lecture Notes in Computer Science, vol 8286. Springer, Cham. https://doi.org/10.1007/978-3-319-03889-6_24
Download citation
DOI: https://doi.org/10.1007/978-3-319-03889-6_24
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-03888-9
Online ISBN: 978-3-319-03889-6
eBook Packages: Computer ScienceComputer Science (R0)