Brown, DaneBradshaw, K2017-07-282017-07-282016-05Brown, D. and Bradshaw, K. 2016. An investigation of face and fingerprint feature-fusion guidelines. 12th International Conference on Beyond Databases, Architectures and Structures. Advanced Technologies for Data Mining and Knowledge Discovery, 31 May - 3 June 2016, Ustron, Poland, p. 585-599. DOI: 10.1007/978-3-319-34099-9_45978-3-319-34099-9https://link.springer.com/chapter/10.1007/978-3-319-34099-9_45DOI: 10.1007/978-3-319-34099-9_45http://hdl.handle.net/10204/9279Copyright: 2016 Springer. Due to copyright restrictions, the attached pdf contains the author-accepted version of the paper. For access to the published version, kindly consult the publisher's website.There are a lack of multi-modal biometric fusion guidelines at the feature-level. This paper investigates face and fingerprint features in the form of their strengths and weaknesses. This serves as a set of guidelines to authors that are planning face and fingerprint feature-fusion applications or aim to extend this into a general framework. The proposed guidelines were 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.enFrameworkFaceFingerprintFeature-levelMulti-modal biometricsConference PresentationBrown, D., & Bradshaw, K. (2016). An investigation of face and fingerprint feature-fusion guidelines. Springer. http://hdl.handle.net/10204/9279Brown, Dane, and K Bradshaw. "An investigation of face and fingerprint feature-fusion guidelines." (2016): http://hdl.handle.net/10204/9279Brown D, Bradshaw K, An investigation of face and fingerprint feature-fusion guidelines; Springer; 2016. http://hdl.handle.net/10204/9279 .TY - Conference Presentation AU - Brown, Dane AU - Bradshaw, K AB - There are a lack of multi-modal biometric fusion guidelines at the feature-level. This paper investigates face and fingerprint features in the form of their strengths and weaknesses. This serves as a set of guidelines to authors that are planning face and fingerprint feature-fusion applications or aim to extend this into a general framework. The proposed guidelines were 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. DA - 2016-05 DB - ResearchSpace DP - CSIR KW - Framework KW - Face KW - Fingerprint KW - Feature-level KW - Multi-modal biometrics LK - https://researchspace.csir.co.za PY - 2016 SM - 978-3-319-34099-9 T1 - An investigation of face and fingerprint feature-fusion guidelines TI - An investigation of face and fingerprint feature-fusion guidelines UR - http://hdl.handle.net/10204/9279 ER -