AffiliationQueen's University, Belfast
MetadataShow full item record
AbstractA practically viable multi-biometric recognition system should not only be stable, robust and accurate but should also adhere to real-time processing speed and memory constraints. This study proposes a cascaded classiﬁer-based framework for use in biometric recognition systems. The proposed framework utilises a set of weak classiﬁers to reduce the enrolled users’ dataset to a small list of candidate users. This list is then used by a strong classiﬁer set as the ﬁnal stage of the cascade to formulate the decision. At each stage, the candidate list is generated by a Mahalanobis distance-based match score quality measure. One of the key features of the authors framework is that each classiﬁer in the ensemble can be designed to use a different modality thus providing the advantages of a truly multimodal biometric recognition system. In addition, it is one of the ﬁrst truly multimodal cascaded classiﬁer-based approaches for biometric recognition. The performance of the proposed system is evaluated both for single and multimodalities to demonstrate the effectiveness of the approach.
CitationBaig, A., Bouridane, A., Kurugollu, F. and Albesher, B., (2013). 'Cascaded multimodal biometric recognition framework'. IET biometrics, 3(1), pp.16-28. DOI: 10.1049/iet-bmt.2012.0043.