Authors:
El Mehdi Cherrat
1
;
Rachid Alaoui
2
and
Hassane Bouzahir
3
Affiliations:
1
ISTI Laboratory, National School of Applied Sciences, Ibn Zohr University, Agadir, Morocco, ASTIMI Laboratory, Higher School of Technology- Sale-, Mohammed V University, Rabat, Morocco, Morocco
;
2
ISTI Laboratory, National School of Applied Sciences, Ibn Zohr University, Agadir, Morocco, ASTIMI Laboratory, Higher School of Technology- Sale-, Mohammed V University, Rabat
;
3
ISTI Laboratory, National School of Applied Sciences, Ibn Zohr University, Agadir, Morocco, ISTI Laboratory, National School of Applied Sciences, Ibn Zohr University, Agadir
Keyword(s):
Fingerprint Recognition; Finger Vein Recognition, Minutiae points, Histogram of Oriented Gradients, Feature Fusion.
Abstract:
The multimodal identification system can integrate a variety of biometric characteristics. The main advan-tage of multibiometric system against traditional single biometric is achieving the recognition process more accurate and safe. In this paper, we will present a multimodal biometric recognition system that combines fingerprint and finger vein. In first step level, the fingerprint image is enhanced based on gabor filter algorithm and binarized. Moreover, it is passed to thinning technique, extract minutiae points and finally the matching. If the matching score is greater than the given fingerprint threshold then recognition is stopped. Else, the second level is started with fingervein image. The orientation correction, ROI detection based on canny method and local histogram equalization are applied to improve the quality of fingervein image. After that, the important features are extracted using HOG method. In the other level, the recognition of the both biometrics sources are ver
ified at decision level fusion based on AND rule. The simulation results have demonstrated that the proposed fusion algorithm performs increase probability the accuracy to 99,85 than the other system based on unimodal characteristics
(More)