Fingerprint Identification using Discretization Technique

Fingerprint based identification system; one of a well known biometric system in the area of pattern recognition and has always been under study through its important role in forensic science that could help government criminal justice community. In this paper, we proposed an identification framework of individuals by means of fingerprint. Different from the most conventional fingerprint identification frameworks the extracted Geometrical element features (GEFs) will go through a Discretization process. The intention of Discretization in this study is to attain individual unique features that could reflect the individual varianceness in order to discriminate one person from another. Previously, Discretization has been shown a particularly efficient identification on English handwriting with accuracy of 99.9% and on discrimination of twins- handwriting with accuracy of 98%. Due to its high discriminative power, this method is adopted into this framework as an independent based method to seek for the accuracy of fingerprint identification. Finally the experimental result shows that the accuracy rate of identification of the proposed system using Discretization is 100% for FVC2000, 93% for FVC2002 and 89.7% for FVC2004 which is much better than the conventional or the existing fingerprint identification system (72% for FVC2000, 26% for FVC2002 and 32.8% for FVC2004). The result indicates that Discretization approach manages to boost up the classification effectively, and therefore prove to be suitable for other biometric features besides handwriting and fingerprint.

Authors:

• W. Y. Leng
• S. M. Shamsuddin

Keywords:

• Discretization
• fingerprint identification
• geometrical features
• pattern recognition

References:

[1] N.K. Ratha, K. Karu, S. Chen, A.K. Jain. A Real-Time Matching System
for Large Fingerprint Databases. IEEE Trans. Pattern Anal. Mach.
Intell., 1996: 799-813.
[2] N. Nain, B.M. Deepak, D. Kumar, M. Baswal, and B. Gautham,
Optimized Minutiae-Based Fingerprint Matching. Lecture Notes
in Engineering and Computer Science, vol. 2170(1), pp.
682-687,2008.
[3] M.K. Umair, A.K. Shoab, N. Ejaz, and R. Riaz, "A Fingerprint
Verification System using Minutiae and. Wavelet Based Features,"
International Conference on Emerging. Technologies, pp. 291-296,
2009.
[4] K. Abbad, N. Assem, H. Tairi and A. Aarab, "Fingerprint Matching
Relying on Minutiae Hough Clusters", ICGST-International Journal on
Graphics, Vision and Image Processing, vol. 10(1), 2010.
[5] B. Roli, S. Priti and B. Punam, "Effective Morphological Extraction of
True Fingerprint Minutiae based on the Hit or Miss Transform"
International Journal of Biometric and Bioinformatics, vol. 4(2), pp. 71-
85, 2010.
[6] Y. Yin, J.Tian and X.K Yang," Ridge Distance Estimation in
Fingerprint Images: Algorithm and Performance Evaluation"
EURASIP Journal on Applied Signal Processing, 2004.
[7] A K Jain and F Farrokhnia. "Unsupervised texture segmentation using
Gabor filters". Pattern Recognition. vol. 12, 1991, pp.238-241.
[8] S Greenberg, M Aladjem, D Kogan and I. Dimitrov. "Fingerprint image
enhancement using filtering techniques". Proceeding 15th Internat.
Conference on Pattern Recognition III. Barcelona, Spain. 2000, pp.326-
329.
[9] B. G. Kim and D.J. Park, ÔÇÿÔÇÿAdaptive image normalization based on
block processing for enhancement of fingerprint image", Electronics
Letters, IEE, Volume 38, Isuue:14, p.p 696-698.
[10] A. Mishra and M. Shandilya, "Fingerprint-s Core Point
Detection Using Gradient Field Mask" International Journal of
Computssser Applications (0975 - 8887), Volume 2 - No.8,
June 2010.
[11] A. K. Jain, L. Hong, S. Pankanti, and R. Bolle, "An identity
authentication system using fingerprints," Proc. IEEE, vol. 85, pp.
1365-1388, Sept. 1997.
[12] E. C. Driscoll, C. O. Martin, K. Ruby, J. J. Russel, and J. G. Watson,
"Method and apparatus for verifying identity using image correlation,"
U.S. Patent 5 067 162, 1991.
[13] A. Sibbald, "Method and apparatus for fingerprint characterization and
recognition using auto-correlation pattern," U.S. Patent 5 633 947, 1994.
[14] D. K. Karna, S. Agarwal, and S. Nikam, "Normalized Cross-correlation
based Fingerprint Matching," in Fifth International Conference on
Computer Graphics, Imaging and Visualization, 2008, pp. 229 - 232.
[15] A. K. Jain, L. Hong, and R. Bolle, "On-line Fingerprint Verification,"
IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.
19, pp. 302 - 314, April, 1997, 1997.
[16] A.K. Muda, S.M. Shamsuddin. and M. Darus, "Invariants Discretization
for Individuality Representation in Handwritten Authorship,"
International Workshop on Computational Forensic (IWCF 2008),
LNCS 5158, Springer Verlag, pp. 218- 228.
[17] B. O. Mohammed and S. M. Shamsuddin, Feature Discretization for
Individuality Representation in Twins Handwritten Identification,
Journal of Computer Science 7(7) (2011), pp. 1080-1087.
[18] W. D. Fisher, On grouping for maximum homogeneity, Journal of the
American Statistical Association 53(284) (1958), pp. 789-798.
[19] J. Dougherty, R. Kohavi and M. Sahami, Supervised and unsupervised
discretization of continuous features, in A. Prieditis & S. Russell (Eds.),
in Int. Conf. on Machine Learning (San Francisco, 1995), pp. 194-202.
[20] M. C. Ludl and G. Widmer, Relative Unsupervised Discretization for
Association Rule Mining, in European Conference on Principles of
Data Mining and Knowledge Discovery (European, 2000), pp. 148-158.
[21] R. Ahmad, M. Darus, S. M. Shamsuddin and A. A. Bakar, Pendiskretan
Set Kasar Menggunakan Ta-akulan Boolean Terhadap Pencaman Simbol
Matematik, Information Technology & Multimedia (2004) 15-26.
[22] A. Kumar and D. Zhang, Hand geometry recognition using entropybased
discretization, IEEE Transaction on Information Forensics and
Security 2 (2) (2007), pp. 181-187.
[23] J. Zou and C. C. Liu, Discretized Gabor Statistical Models for Face
Recognition, Digital Content Technology and its Applications (JDCTA)
5(5) (2011), pp. 175-181.
[24] K. Kianmehr, M. Alshalalfa and R. Alhajj, Fuzzy clustering-based
discretization for gene expression classification, Knowledge and
Information Systems (Published online, 2009).
[25] K. Sarojini, K. Thangavel and D. DXevakumari, Feature Subset
Selection based on Modified Fuzzy Relative Information Measure for
classifier, Engineering Science and Technology 2(5) (2010) 2456-2465.
[26] J. Gama and C. Pinto, Discretization from Data Streams: applications to
Histograms and Data Mining, in ACM Symposium on Applied
Computing, (ACM Press, New York, 2006), pp. 662-667.
[27] M.M. Min and Y. Thein, "Intelligent Fingerprint Recognition System by
Using Geometry Approach" IEEE International Conference on Current
Trends in Information Technology,pp.1-5,2009
[28] M. Poulos, E. Magkos, V. Chrissikopoulos, N. Alexandris, "Secure
fingerprint verification based on image processing segmentation using
computational geometry algorithms", 2003
[29] C. Lee and D. G. H. Shin, A context-sensitive discretization of numeric
attributes for classification learning. In: Proceedings of the eleventh
European conference on artificial intelligence. Amsterdam: Wiley;
1994.p. 428-32
[30] C.H. Wu, "Advance Feature Extraction Algorithms for Automatic
Fingerprint Recognition Systems", Dissertation on The University of
New York, April 2007.
[31] J. Komorowski, A. ├ÿhrn and A. Skowron (2002). The ROSETTA
Rough Set Software System, In Handbook of Data Mining and
Knowledge Discovery, W. Klösgen and J. Zytkow (eds.), ch. D.2.3,
Oxford University Press. ISBN 0-19-511831-6.