Biometric Authentication Using Kekre's Wavelet Transform

This paper proposes an enhanced method for personal authentication based on finger Knuckle Print using Kekre's wavelet transform (KWT). Finger-knuckle-print (FKP) is the inherent skin patterns of the outer surface around the phalangeal joint of one's finger. It is highly discriminable and unique which makes it an emerging promising biometric identifier. Kekre's wavelet transform is constructed from Kekre's transform. The proposed system is evaluated on prepared FKP database that involves all categories of FKP. The total database of 500 samples of FKP. This paper focuses the different image enhancement techniques for the pre-processing of the captured images. The proposed algorithm is examined on 350 training and 150 testing samples of database and shows that the quality of database and pre-processing techniques plays important role to recognize the individual. The experimental result calculate the performance parameters like false acceptance rate (FAR), false rejection rate (FRR), True Acceptance rate (TAR), True rejection rate (TRR). The tested result demonstrated the improvement in EER (Error Equal Rate) which is very much important for authentication. The experimental result using Kekre's algorithm along with image enhancement shows that the finger knuckle recognition rate is better than the conventional method.

[1]  Damon L. Woodard,et al.  Finger surface as a biometric identifier , 2005, Comput. Vis. Image Underst..

[2]  G. Sainarayanan,et al.  Palmprint identification using wavelet energy , 2007, 2007 International Conference on Intelligent and Advanced Systems.

[3]  Damon L. Woodard,et al.  Personal identification utilizing finger surface features , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[4]  M. Sujatha,et al.  Recognition of Human Iris Patterns for Biometric Identification , 2015 .

[5]  H. B. Kekre,et al.  Finger-Knuckle-Print verification using Kekre's wavelet transform , 2011, ICWET.

[6]  Mario Baum,et al.  Handbook Of Biometrics , 2016 .

[7]  Sharath Pankanti,et al.  Filterbank-based fingerprint matching , 2000, IEEE Trans. Image Process..

[8]  S. Shekhar,et al.  Personal Identification Using Multibiometrics Rank-Level Fusion , 2011, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[9]  Ajay Kumar,et al.  Technical Correspondence Personal Identification Using Multibiometrics Rank-Level Fusion , 2011 .

[10]  Phalguni Gupta,et al.  An Efficient Finger-Knuckle-Print Based Recognition System Fusing SIFT and SURF Matching Scores , 2011, ICICS.

[11]  Madasu Hanmandlu,et al.  Feature Selection for Finger Knuckle Print-based Multimodal Biometric System , 2012 .

[12]  Libor Masek,et al.  Recognition of Human Iris Patterns for Biometric Identification , 2003 .

[13]  David Zhang,et al.  Online Palmprint Identification , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[14]  Ajay Kumar,et al.  Personal Authentication Using Finger Knuckle Surface , 2009, IEEE Transactions on Information Forensics and Security.

[15]  David Zhang,et al.  On-Line Palmprint Identification , 2005 .

[16]  Zhenhua Guo,et al.  Phase congruency induced local features for finger-knuckle-print recognition , 2012, Pattern Recognit..