Language and Style Advisors
G. Baskaran, Ph.D.
Sam Mohanlal, Ph.D.
|
Back Issues of Engineering & Technology in India - From 2016
BOOKS FOR YOU TO READ AND DOWNLOAD FREE!
BACK ISSUES
Copyright © 2015 |
Human Identification Using FKP, IRIS and FV ImagesK. Velkumar and M. BhavaniAbstract Biometric Recognition will provide strong link between individual and claimed identity. In modern years, biometrics is largely used for personal recognition. In this paper, a new combined biometric system, namely, Finger-Knuckle-Print (FKP), Finger vein and IRIS, is proposed. We can extract the FKPs features by Linear Discriminate Analysis (LDA), and Finger Vein and IRIS features by the 2D Block based on Gabor method. Finally, performance of all finger knuckle, vein and iris are determined individually and a min rule fusion is applied to develop a combined authentication system. Experimental results show that LDA is the best performance for identifying FKPs, and Gabor is the best performance for IRIS as well as Finger vein and it is able to provide an excellent recognition rate and more security. Keywords: Finger Knuckle Print, IRIS, LDA, Finger Vein, Gabor, Recognition. Introduction Biometrics is used to identify a person using one’s physiological or characteristics Human physiological and/or behavioural characteristic can be used as a biometric feature when it satisfies the requirements as ubiquity, peculiarity, stability and collectability. Well known Biometric features are fingerprints, hand veins, handwritten signatures, retinal patterns, ear patterns, etc. Hand-based biometrics has been fascinating considerable attention over present years due to its ease in accession. Presently, it is noticed that the dorsum of hand has the potential to do personal authentication. The texture pattern is captured by bending the finger knuckle of a person, and it is hugely unique and thus can serve as a distinct biometric feature. The user acceptance for the outer finger surface imaging can be very huge as, unlike attractive fingerprints, there is no stigma of criminal examination associated with finger knuckle surface imaging [2]. The peg-free imaging of the finger knuckle surface is hugely convenient to users and offers very huge potential for reliable personal identification and authentication. The appearance based approach examination in for the finger knuckle identification cannot exploit line based features and therefore achieves quality performance. The finger knuckle surface is hugely rich in lines and creases, which are fairly curved but hugely unique for individuals. K. Velkumar
|