Confidence Based Rank Level Fusion for Multimodal Biometric Systems
Multimodal biometric systems have proven advantages over single biometric systems as they are using multiple traits of users. The intra-class variance provided by using more than one trait results in a high identification rate. Still, one of the missing parts in a multimodal system is inattention to the discriminability of each rank list for each specific user. This paper introduces a novel approach to select a combination of rank lists in rank level so that it provides the highest discrimination for any specific query. The rank list selection is based on pseudo-scores lists that are created by combination of rank lists and resemblance probability distribution of users. The experimental results on a multimodal biometric system based on frontal face, profile face, and ear indicated higher identification rate by using novel confidence based rank level fusion.
KeywordsMultimodal biometrics Rank level fusion Rank list selection Resemblance probability distribution
Unable to display preview. Download preview PDF.
- 1.Ross, A.A., Nandakumar, K., Jain, A.K.: Handbook of multibiometrics. Springer Science & Business Media (2006)Google Scholar
- 2.Jain, A.K., Flynn, P., Ross, A.A.: Handbook of biometrics. Springer Science & Business Media (2007)Google Scholar
- 3.Revett, K.: Behavioral biometrics: a remote access approach. John Wiley & Sons (2008)Google Scholar
- 6.Bhatnagar, J., Kumar, A., Saggar, N.: A novel approach to improve biometric recognition using rank level fusion. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2007, pp 1–6. IEEE (2007)Google Scholar
- 9.Monwar, M.M., Gavrilova, M., Wang, Y.: A novel fuzzy multimodal information fusion technology for human biometric traits identification. In: 2011 10th IEEE International Conference on Cognitive Informatics & Cognitive Computing (ICCI* CC), pp. 112–119. IEEE (2011)Google Scholar
- 10.Marasco, E., Abaza, A., Cukic, B.: Why rank-level fusion? and what is the impact of image quality?Google Scholar
- 11.Abaza, A., Ross, A.: Quality based rank-level fusion in multibiometric systems. In: IEEE 3rd International Conference on Biometrics: Theory, Applications, and Systems, BTAS 2009, pp. 1–6. IEEE (2009)Google Scholar
- 12.Alam, M.R., Bennamoun, M., Togneri, R., Sohel, F.: Confidence-based rank-level fusion for audio-visual person identification system. In: 3rd International Conference on Pattern Recognition Applications and Methods, 2014, pp. 608–615 (2014)Google Scholar
- 14.Talebi, H., Gavrilova, M.: Prior resemblance probability of users for multimodal biometrics rank fusion. In: IEEE International Conference on Identity, Security and Behavior Analysis (ISBA 2015). IEEE (2015)Google Scholar
- 15.Monwar, M., Gavrilova, M.: Fes: a system for combining face, ear and signature biometrics using rank level fusion. In: Fifth International Conference on Information Technology: New Generations, 2008, pp. 922–927. IEEE (2008)Google Scholar
- 16.Bhattacharyya, A.: On a measure of divergence between two multinomial populations. Sankhyā: The Indian Journal of Statistics, 401–406 (1946)Google Scholar
- 18.USTB ear database, china. http://www.ustb.edu.cn/resb/ (accessed May 11, 2008)