| Author and year | Biometric modalities | Fusion level | Approach used |
| Nandakumar et al., 2008 [4] | Face, fingerprint, speech, iris | Matching score level | Likelihood ratio-based fusion | Maurer and Baker, 2008 [38] | Fingerprint, speech | Matching score level, quality-based fusion | Quality estimates via a Bayesian belief network (modified sum-rule) | Poh et al., 2009 [39] | Face, fingerprint, iris | Matching score level | Benchmarking 22 different biometric fusion algorithms |
Lin and Yang, 2012 [40] | Face |
Matching score level | Enhanced score-level fusion based on boosting | Tao and Veldhuis, 2009 [21] | Face (two face recognition algorithms) | Matching score level, decision level | Optimal fusion scheme at decision level by AND- or OR-rule (score levels: sum-rule, likelihood ratio, SVM) | Vatsa et al., 2010 [41] | Face (two face recognition algorithms) | Matching score level | Sequential fusion algorithm (likelihood ratio test + SVM) | Poh et al., 2010 [42] | Face, fingerprint | Matching score level | Quality-based score normalization | Poh et al., 2010 [43] | Face, fingerprint, iris | Matching score level | Addressing missing values in multimodal system with neutral point method | Nanni et al., 2011 [44] | Fingerprint, palm print, face |
Matching score level | Likelihood ratio, SVM, AdaBoost of neural networks | Poh and Kittler, 2012 [45] | Face, fingerprint | Matching score level, quality-based fusion | A general Bayesian framework | Nagar et al., 2012 [46] | Face, fingerprint, iris | Feature level | Feature level fusion framework using biometric cryptosystems | Tao and Veldhuis, 2013 [47] | Face, speech | Matching score level | Native likelihood ratio via ROC |
|
|