Abstract

Recently, several biometric technologies are considered mature enough to be a new tool for security and Finger-Knuckle-Print (FKP) based person identification is one of these technologies. This technology provides a reliable, low cost and user-friendly viable solution for a range of access control applications. Also, their rich texture information offers one of the powerful means in personal identification. In this paper, we propose a multi-algorithmic based biometric system for person recognition using FKP images. Thus, to extract the FKPs features, both, the 1D Log-Gabor Filter (LGF) response and Local Binary Pattern (LBP) descriptor are employed. Finally, performance of each technique is determined individually and a fusion at matching score level is applied to develop a multimodal system. Experimental results show that FKP modalities yields the best performance for identifying persons and it is able to provide an excellent identification rate and provide more security.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call