Biometric scores fusion based on total error rate minimization
Pattern Recognition
Fusion of visual and infra-red face scores by weighted power series
Pattern Recognition Letters
Information Fusion in Multimedia Information Retrieval
Adaptive Multimedial Retrieval: Retrieval, User, and Semantics
Can feature information interaction help for information fusion in multimedia problems?
Multimedia Tools and Applications
An Empirical Study of a Linear Regression Combiner on Multi-class Data Sets
MCS '09 Proceedings of the 8th International Workshop on Multiple Classifier Systems
True Path Rule Hierarchical Ensembles
MCS '09 Proceedings of the 8th International Workshop on Multiple Classifier Systems
Biometric Recognition: When Is Evidence Fusion Advantageous?
ISVC '09 Proceedings of the 5th International Symposium on Advances in Visual Computing: Part II
Benchmarking quality-dependent and cost-sensitive score-level multimodal biometric fusion algorithms
IEEE Transactions on Information Forensics and Security - Special issue on electronic voting
IEEE Transactions on Information Forensics and Security
Robust fusion: extreme value theory for recognition score normalization
ECCV'10 Proceedings of the 11th European conference on computer vision conference on Computer vision: Part III
Fusion in fingerprint authentication: two finger types vs. two scanner types
Proceedings of the 2011 ACM Symposium on Applied Computing
Error-rate based biometrics fusion
ICB'07 Proceedings of the 2007 international conference on Advances in Biometrics
Hi-index | 35.68 |
Combining multiple information sources such as subbands, streams (with different features) and multimodal data has been shown to be a very promising trend, both in experiments and to some extents in real-life biometric authentication applications. Despite considerable efforts in fusions, there is a lack of understanding on the roles and effects of correlation and variance (of both the client and impostor scores of base-classifiers/experts). Often, scores are assumed to be independent. In this paper, we explicitly consider this factor using a theoretical model, called variance reduction-equal error rate (VR-EER) analysis. Assuming that client and impostor scores are approximately Gaussian distributed, we showed that equal error rate (EER) can be modeled as a function of F-ratio, which itself is a function of 1) correlation; 2) variance of base-experts; and 3) difference of client and impostor means. To achieve lower EER, smaller correlation and average variance of base-experts, and larger mean difference are desirable. Furthermore, analysing any of these factors independently, e.g. focusing on correlation alone, could be miss-leading. Experimental results on the BANCA multimodal database confirm our findings using VR-EER analysis. We analyzed four commonly encountered scenarios in biometric authentication which include fusing correlated/uncorrelated base-experts of similar/different performances. The analysis explains and shows that fusing systems of different performances is not always beneficial. One of the most important findings is that positive correlation "hurts" fusion while negative correlation (greater "diversity", which measures the spread of prediction score with respect to the fused score), improves fusion. However, by linking the concept of ambiguity decomposition to classification problem, it is found that diversity is not sufficient to be an evaluation criterion (to compare several fusion systems), unless measures are taken to normalize the (class-dependent) variance. Moreover, by linking the concept of bias-variance-covariance decomposition to classification using EER, it is found that if the inherent mismatch (between training and test sessions) can be learned from the data, such mismatch can be incorporated into the fusion sys- tem as a part of training parameters.