Feature-level fusion of fingerprint and finger-vein for personal identification
Abstract
Multimodal biometrics based on feature-level fusion is a significant topic in personal identification research community. In this paper, a new fingerprint-vein based biometric method is proposed for making a finger more universal in biometrics. The fingerprint and finger-vein features are first exploited and extracted using a unified Gabor filter framework. Then, a novel supervised local-preserving canonical correlation analysis method (SLPCCAM) is proposed to generate fingerprint-vein feature vectors (FPVFVs) in feature-level fusion. Based on FPVFVs, the nearest neighborhood classifier is employed for personal identification finally. Experimental results show that the proposed approach has a high capability in fingerprint-vein based personal recognition as well as multimodal feature-level fusion.
- Publication:
-
Pattern Recognition Letters
- Pub Date:
- April 2012
- DOI:
- 10.1016/j.patrec.2011.11.002
- Bibcode:
- 2012PaReL..33..623Y
- Keywords:
-
- Multimoadl biometrics;
- Finger-vein;
- Fingerprint;
- Canonical correlation analysis