Open Access Open Access  Restricted Access Subscription or Fee Access

A KPCA-based Biometric Identifier Using Finger Knuckle Surface

Paul Augustine, J. Dinesh Peter


Biometrics deals with human intrinsic physical or behavioral patterns. It is divided into physiological and behavioral types. Biometric authentication using finger knuckle surface is a new technique. The fingers have to be kept wide open while imaging. The image has to be taken in a white background. The knuckle surface of each human being is unique in nature. Various finger geometrical calculations are needed for the extraction of knuckles. In this approach various techniques used for feature extraction of finger knuckle surface is mentioned in a detailed manner. The various techniques used here are ICA (Independent Component Analysis) , LDA (Linear Discriminant Analysis), PCA (Principal Component Analysis) and KPCA (Kernel Principal Component Analysis). The main aim is to find which feature extraction technique gives better performance in case of finger knuckle surface authentication. The usage of KPCA method helps in attaining better results. The experimental results graphs are plotted for each knuckle separately and which technique gives better performance is noted.


Biometrics, FAR, Finger Knuckle Surface, Finger Geometry, ROC

Full Text:



Ajay Kumar and Ch. Ravikanth, “Personal Authentication Using Finger Knuckle Surface”, IEEE Transactions On Information Forensics And Security, vol. 4, no. 1, march 2009.

Bernard scholkopf, Alexander smola, Klaus-robert miller, “kernel principal component analysis”, maxplanck institute,spemannstr.38,72076 tibingen germany.

Kresimir Delac, Mislav Grgic and Sonja Grgic “ Independent Comparative Study of PCA, ICA, and LDA on the FERET Data Set”, University of Zagreb, FER, Unska 3/XII, Zagreb, Croatia Vol. 15, 252–260 february2006.

G. L. Marcialis and F. Roli, “Fusion of LDA and PCA for face verification,” in Proc. ECCV Workshop Biometric Authentication, 2002, pp.30–38.

C. Havran, L. Hupet, J. Czyz, J. Lee, L. Vandendorpe, M. Verleysen “Independent Component Analysis for face authentication” Knowledge-Based Intelligent Information and Engineering Systems September 2002.

R. K. Rowe, U. Uludag, M. Demirkus, S. Parthasaradhi and A. K. Jain, “A multispectral whole-hand biometric authentication system,” Proc. Biometric Symposium, Baltimore, Sep. 2007.

X. Lu, Y.Wang, and A. K. Jain, “Combining classifiers for face recognition,” in Proc. ICME, Jul. 2003, vol. 3, pp. 13–16.

D. Zhang, W. K. Kong, J. You, and M.Wong, “On-line palmprint identification,”IEEE Trans. Pattern Anal. Mach. Intell., vol. 25, no. 9, pp.1041–1050, Sep. 2003.

A. K. Jain, A. Ross, and S. Pankanti, “A prototype hand geometry based verification system,” in Proc. 2nd Int. Conf. Audio and Video-Based Biometric Person Authentication, Washington, DC, pp. 166–171, Mar. 1999.

S. Ribaric and I. Fratric, “A biometric identification system based on eigenpalm and eigenfinger features,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 27, no. 11, pp. 1698–1709, Nov. 2005.

X. Jiang, W. Xu, L. Sweeney, Y. Li, R. Gross, and D. Yurovsky, “New directions in contact free hand recognition,” in Proc. ICIP, pp.389–392, 2007.

D. L. Woodard and P. J. Flynn, “Finger surface as a biometric identifier,”Comput. Vis. Image Understanding, vol. 100, pp. 357–384, Aug 2005.

C.-L. Lin and K.-C. Fan, “Biometric verification using thermal images of palm-dorsa vein patterns,” IEEE Trans. Circuits Syst. Video Technol., vol. 14, no. 2, pp. 199–213, Feb. 2004.

A.Kumar and D. Zhang, “Personal authentication using multiple palmprint representation,” Pattern Recogn., vol. 38, pp. 1695–1704, Mar.2005.

Lin Zhang, Lei Zhang, David Zhang and Hailong Zhu, “Online Finger-Knuckle-Print Verification for Personal Authentication” Biometrics Research Center, Department of Computing, The Hong Kong Polytechnic University.

Yong Xu, David Zhang, Fengxi Song, Jing-Yu Yang, Zhong Jing, Miao Li “A method for speeding up feature extraction based on KPCA” science direct Neurocomputing 70 (2007) 1056–1061.


  • There are currently no refbacks.

Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.