The lack of multi-biometric fusion guidelines at the feature-level are addressed in this work. A feature-fusion framework is geared toward improving human identification accuracy for both single and multiple biometrics. The foundation of the framework is the improvement over a state-of-the-art uni-modal biometric verification system, which is extended into a multi-modal identification system. A novel multi-biometric system is thus designed based on the framework, which serves as fusion guidelines for multi-biometric applications that fuse at the feature-level. This framework was applied to the face and fingerprint to achieve a 91.11% recognition accuracy when using only a single training sample. Furthermore, an accuracy of 99.69% was achieved when using five training samples.
Reference:
Brown, D. and Bradshaw, K. 2016. A multi-biometric feature-fusion framework for improved uni-modal and multi-modal human identification. 2016 IEEE Symposium on Technologies for Homeland Security (HST), 10-12 11 May 2016, Waltham, MA, USA. DOI: 10.1109/THS.2016.7568927
Brown, K., & Bradshaw, K. (2016). A multi-biometric feature-fusion framework for improved uni-modal and multi-modal human identification. IEEE. http://hdl.handle.net/10204/9240
Brown, K, and K Bradshaw. "A multi-biometric feature-fusion framework for improved uni-modal and multi-modal human identification." (2016): http://hdl.handle.net/10204/9240
Brown K, Bradshaw K, A multi-biometric feature-fusion framework for improved uni-modal and multi-modal human identification; IEEE; 2016. http://hdl.handle.net/10204/9240 .
Copyright: 2016 IEEE. Due to copyright restrictions, the attached PDF file contains the accepted version of the full text item. For access to the published version, kindly consult the publisher's website.