Escolar Documentos
Profissional Documentos
Cultura Documentos
HTTPS://SITES.GOOGLE.COM/SITE/JOURNALOFCOMPUTING/
WWW.JOURNALOFCOMPUTING.ORG 101
Abstract— Presently personal identification using fingerprint is one of the most reliable and popular biometric recognition
method. An accurate and consistent classification algorithm can significantly reduce fingerprint matching time. This paper
describes Extended Fuzzy Hypersphere Neural Network (EFHSNN) with its learning algorithm, which is an extension of Fuzzy
Hypersphere Neural Network (FHSNN). The EFHSNN uses Manhattan distance instead of Euclidian distance. The experimental
results for PolyU HRF fingerprint database show that EFHSNN is superior and yields 100% recognition rate along with less
training and recall time.
Index Terms— Biometrics, Fuzzy Neural Network, Hypersphere, Fingerprint Recognition, FingerCode.
—————————— ——————————
1 INTRODUCTION
TABLE 1
4. A.K. Jain, L. Hong, S. Pankanti, and R. Bolle, “An identity au‐
TIMING ANALYSIS
thentication system using fingerprints”, Proceedings of the IEEE,
Classifier Average Training Average Vol. 85, No. 9, pp. 1365‐1388, 1997.
Time (Seconds) Recall
Time 5. A. K. Hrechak and I. A. Mchugh, “Automated fingerprint recogni‐
(Seconds) tion using structural matching”, Pattern Recognition, vol. 23, no.
FHSNN using Euc- 0.463710 4.000131 8, pp. 893‐904, 1990.
lidian distance
6. A. K. Jain, S. Prabhakar, and L. Hong, “A multichannel approach
EFHSNN using 0.450811 3.686820
to Fingerprint Classification”, IEEE Transactions on Pattern
Manhattan distance
Analysis and Machine Intelligence, vol. 21, no. 4, pp. 348‐359,
1999.
TABLE 2
PERCENTAGE RECOGNITION RATE WITH FHSNN AND EFHSNN 7. A. K. Jain, S. Prabhakar, L. Hong, and S, Pankanti, “FingerCode:
Classifier Radius Hyper- Recognition a FilterBank for fingerprint representation and matching”, Proceed‐
spheres Rate ings of IEEE Computer Society Conference on Computer Vision
and Pattern Recognition(CVPR), vol. 2, pp. 187‐ 193, 1999.
FHSNN 0.0249 280 100 %
EFHSNN 0.09 262 100 % 8. A. K. Jain, S. Prabhakar, L. Hong, and S. Pankanti, “FilterBank‐
based fingerprint matching”, IEEE Transactions on Image
radius and recognition rate are depicted in Table2. Processing, vol. 9, no. 5, pp. 846‐859, 2000.
9. U.V. Kulkarni and T.R. Sontakke, “Fuzzy Hypersphere Neural
As shown in Table 1 the training and testing time
Network Classifier”, Proceedings of 10th International IEEE Con‐
(0.450811, 3.686820 seconds respectively) of EFHSNN ference on Fuzzy Systems, University of Melbourne, Australia,
classifier is fast compared to any other classifier. Also as December 2001, pp. 1559‐1562.
shown in Table 2 the number of hyperspheres (262) is also
less in comparison with FHSNN. Hence, the EFHSNN 10. J. G. Daugman, “High confidence recognition of persons by a test of
statistical independence”, IEEE Transactions on Pattern Analysis
classifier gives better recognition rates in comparison
and Machine Intelligance, vol. 15, no. 11, pp. 1148–1161, 1993.
with FHSNN in terms of less number of hyperspheres,
training and recall time. 11. J. G. Daugman, “Uncertainty relation for resolution in space, spatial
frequency, and orientation optimized by two‐dimensional visual cor‐
tical filters”, J.Opt. Soc. Amer. A. vol. 2, pp. 1160–1169, 1985.
6 CONCLUSIONS
For effective classification of fingerprint in network socie- 12. B. B. M. Krishna Kanth, U. V. Kulkarni and B. G. V. Giridhar,
ty, we have demonstrated effectiveness of EFHSNN clas- “Gene Expression Based Acute Leukemia Cancer Classification: a
sifier on fingerprint dataset. Experimental results shows Neuro‐Fuzzy Approach” International Journal of Biometrics and
that the EFHSNN classifier is the most effective compared Bioinformatics, (IJBB), Volume (4): Issue (4) pp. 136–146, 2010.
with FHSNN classifier in terms of less number of hyper-
M. H. Kondekar received the M.C.A. degree from Government En-
spheres, training and recall time. The training time differ- gineering College, Aurangabad in the year 2000. He received the
ence of 0.012899 seconds and testing time difference of M.Phil. Degree in Computer Science from Y.C.M.O. University, Na-
0.313311 seconds is less as compared with FHSNN clas- shik in the year 2009. He is currently working as Lecturer in the Col-
sifier. Thus EFHSNN can be used for huge realistic data- lege of Computer Science and Information Technology, Latur, Maha-
rastra. His current research interests include various aspects of
base recognition purposes where less amount of training Neural Networks and Fuzzy Logic, Pattern Recogntion and Biome-
and testing time is the prime request. Our future work trics.
will be based on exploring clustering techniques using
fuzzy neural approach. Dr.U.V.Kulkarni received the PhD degree in Electronics and Com-
puter Science Engineering from S.R.T.M. University, Nanded in the
year 2003. He is currently working as Head of Computer Science
REFERENCES Engineering Department and Dean of academics, SGGS Institute of
Engineering and Technology, Nanded, Maharastra.
1. P.Meenen, and R.Adhami, “Fingerprinting for security”, Proceed‐
ings of the IEEE Potentials, pp. 33‐38, 2001.
S. S. Chowhan received the M.Sc.(CS) degree from Dr. BAM Uni-
2. T. Song, Liang Huang, Che‐Wei Liu, Jui‐Peng Lin, Chien‐Ying versity, Aurangabad in the year 2000. He received the M.Phil. De-
Li, and Ting‐Yi Kuo, “A Novel Scheme for Fingerprint Identifica‐ gree in Computer Science from Y.C.M.O. University, Nashik in the
tion”, Proceedings of the Second Canadian Conference on year 2008. He is currently working as lecturer in the College of Com-
Computer and Robot Vision (CRV’05) 0‐7695‐2319‐6/05. puter Science and Information Technology, Latur, Maharastra. His
current research interests include various aspects of Neural Net-
3. W. J. Babler, ʺEmbryologic Development of Epidermal Ridges and works and Fuzzy Logic, Pattern Recogntion and Biometrics.
Their Configurationʺ, Birth Defects Original Article Series, vol.
27, no. 2, 1991.