Finger Vein Recognition Using Local Mean Based K-Nearest Centroid Neighbor Classifier

Abstract:

One of the newest methods of identification system is finger vein recognition which is a unique and successful way to identify human based on the physical characteristics of finger vein patterns. In this paper, a new type of classifier called Local Mean based K-nearest centroid neighbor (LMKNCN) is applied to classify finger vein patterns. Finally, the significance of the proposed method is proven by comparing the results of LMKNCN classifier with traditionally used K nearest neighbor classifier (KNN). The experimental results indicate that the proposed method in this research confidently merits the performance of the finger vein recognition method, as the gained accuracy using the proposed method is higher than that of the traditionally used method KNN. The maximum obtained accuracy of LMKNCN test with 2040 number of finger vein images is 100% while for KNN is 98.53%.

• Periodical: Advanced Materials Research (Volume 628)
• Pages: 427-432
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.628.427
• Online since: December 2012
• Authors: Ali Khalili Mobarakeh, Sayedmehran Mirsafaie Rizi, Saba Nazari, Jiang Ping Gou, Bakhtiar Affendi Rosdi
• Keywords: Biometrics, Finger Vein Recognition, K-Nearest Neighbor (KNN), Local Mean Based K-Nearest Centroid Neighbor (LMKNCN), Principal Component Analysis (PCA)

References

[1] Eui Chul Lee, H.J., Daeyeoul Kim New Finger Biometric Method Using Near Infrared Imaging. Sensors, 2011. 11(3): pp.2319-2333.

DOI: 10.3390/s110302319

[2] Wold, S., K. Esbensen, and P. Geladi, Principal component analysis. Chemometrics and Intelligent Laboratory Systems, 1987. 2(1–3): pp.37-52.

DOI: 10.1016/0169-7439(87)80084-9

[3] Gou, J., et al., A Local Mean-Based k-Nearest Centroid Neighbor Classifier. The Computer Journal, 2012. 55(9): pp.1058-171.

DOI: 10.1093/comjnl/bxr131

[4] Mahri, N., S.A.S. Suandi, and B.A. Rosdi, Finger Vein Recognition Algorithm Using Phase Only Correlation, in Emerging Techniques and Challenges for Hand-Based Biometrics (ETCHB), 2010 International Workshop on. pp.1-6.

DOI: 10.1109/etchb.2010.5559283

[5] Rosdi, B.A., C.W. Shing, and S.A. Suandi, Finger Vein Recognition Using Local Line Binary Pattern. Sensors, 2011. 11(12): pp.11357-11371.

DOI: 10.3390/s111211357

[6] Delac, K., M. Grgic, and S. Grgic, Independent comparative study of PCA, ICA, and LDA on the FERET data set. International Journal of Imaging Systems and Technology, 2005. 15(5): pp.252-260.

DOI: 10.1002/ima.20059

[7] L. K. SAUL, K.Q.W., J. H. HAM, F. SHA, AND D. D. LEE, Spectral Methods for Dimensionality Reduction, MIT Press, Cambridge, MA, 2005.

[8] T. M. Cover, P.E.H., Nearest neighbor pattern classification, in IEEE Transactions on Information Theory1967. pp.21-27.

[9] Fix , E. and J.L. Hodges, Discriminatory Analysis,Nonparametric Discrimination:. Vol. 57. 1951. 238-247.

[10] Sebestyen, G., Pattern recognition by an adaptive process of sample set construction. Information Theory, IRE Transactions on, 1962. 8(5): pp.82-91.

DOI: 10.1109/tit.1962.1057766

[11] Mitani, Y. and Y. Hamamoto, A local mean-based nonparametric classifier. Pattern Recognition Letters, 2006. 27(10): pp.1151-1159.

DOI: 10.1016/j.patrec.2005.12.016