Abstract
The feature extraction, which is the most critical part of biometric recognition systems, is solely done based on expert knowledge or rather intuitively. Thus, no guaranty could be given that extracted features are suitable for biometric user authentication. Moreover, the expert knowledge could be only applied for a particular quality of raw data or only defined for a particular database. Therefore, the feature analysis is required to estimate the discrimination power of extracted features and automatically eliminate all irrelevant or redundant ones. In order to provide a feature ranking and consequent filtering, authors suggest several heuristics and compare these to each other and to several wrapper approaches. The experiments were done on features extracted from dynamic handwriting data. The comparison of feature subsets is provided based on hash generation performance of quantization based secure sketch algorithm. The experiments show a significant increase of reproduction rates (RR) and decrease of collision rates (CR). After feature selection the CR for the most appropriate written content ‘symbol’ reduced from 5.04% to 3.44% and the RR grows from 70.57% to 93.59%. Furthermore, the lower number of features ensures the reduction of computational complexity and, thus, classification speed-up.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Almuallim, H., Dietterich, T.G.: Learning With Many Irrelevant Features. In: Proc. of the Ninth National Conference on Artificial Intelligence, pp. 547–552 (1991)
Balakirsky, V.B., Han Vinckin, A.J.: Biometric Authentication Based on Significant Parameters. In: Vielhauer, C., Dittmann, J., Drygajlo, A., Juul, N.C., Fairhurst, M.C. (eds.) BioID 2011. LNCS, vol. 6583, pp. 13–24. Springer, Heidelberg (2011)
Dash, M., Liu, H.: Feature selection for classification. Journal of Intelligent Data Analysis 1(1-4), 131–156 (1997)
Dodis, Y., Ostrovsky, R., Reyzin, L., Smith, A.: Fuzzy Extractors: How to Generate Strong Keys from Biometrics and Other Noisy Data. SIAM J. Comput. 38(1), 97–139 (2008)
Duda, R.O., Hart, P.E., Stork, D.G.: Pattern Classification, 2nd edn. Wiley-Interscience (2000)
Fiérrez-Aguilar, J., Nanni, L., Lopez-Peñalba, J., Ortega-Garcia, J., Maltoni, D.: An On-Line Signature Verification System Based on Fusion of Local and Global Information. In: Kanade, T., Jain, A., Ratha, N.K. (eds.) AVBPA 2005. LNCS, vol. 3546, pp. 523–532. Springer, Heidelberg (2005)
Guyon, I., Elisseeff, A.: An Introduction to Variable and Feature Selection. Journal of Machine Learning Research 3, 1157–1182 (2003)
Guyon, I., Gunn, S., Nikravesh, M., Zadeh, L.: Feature Extraction, Foundations and Applications. STUDFUZZ. Physica-Verlag, Springer (2006)
Hall, M.A., Smith, L.A.: Practical feature subset selection for machine learning. In: Proc. of the 21st Australian Computer Science Conference, pp. 181–191 (1998)
Jain, A.K., Nandakumar, K., Nagar, A.: Biometric Template Security. EURASIP Journal on Advances in Signal Processing, Article ID 579416 (2008)
John, G.H., Kohavi, R., Pfleger, K.: Irrelevant Features and the Subset Selection Problem. In: Proc. of the International Conference on Machine Learning, pp. 121–129 (1994)
Juels A., Wattenberg, M.: A Fuzzy Commitment Scheme. In: Proc. of the ACM Conference on Computer and Communications Security, pp. 28–36 (1999)
Kira, K., Rendell, L.A.: The feature selection problem: Traditional methods and a new algorithm. In: Proc. 10th National Conference on Artificial Intelligence, pp. 129–134 (1992)
Kohavi, R., John, G.H.: Wrappers for Feature Subset Selection. Journal of Artificial Intelligence 97(1), 273–324 (1997)
Kumar, A., Zhang, D.: Biometric Recognition Using Feature Selection and Combination. In: Kanade, T., Jain, A., Ratha, N.K. (eds.) AVBPA 2005. LNCS, vol. 3546, pp. 813–822. Springer, Heidelberg (2005)
Liu, H., Motoda, H. (eds.): Computational Methods of Feature Selection. Data Mining and Knowledge Discovery Series. Chapman & Hall/ CRC, Taylor & Francis Group, LLC (2008)
Makrushin, A., Scheidat, T., Vielhauer, C.: Handwriting Biometrics: Feature Selection Based Improvements in Authentication and Hash Generation Accuracy. In: Vielhauer, C., Dittmann, J., Drygajlo, A., Juul, N.C., Fairhurst, M.C. (eds.) BioID 2011. LNCS, vol. 6583, pp. 37–48. Springer, Heidelberg (2011)
Molina, L.C., Belanche, L., Nebot, A.: Feature Selection Algorithms: A survey and experimental evaluation. In: Proc. IEEE Int. Conf. on Data Mining, pp. 306–313 (2002)
Pudil, P., Novovicová, J., Kittler, J.: Floating search methods in feature selection. Pattern Recognition Letters 15(11), 1119–1125 (1994)
Saeys, Y., Inza, I., Larrañaga, P.: A review of feature selection techniques in bioinformatics. Bioinformatics 23(19), 2507–2517 (2007)
Scheidat, T., Vielhauer, C., Dittmann, J.: Biometric hash generation and user authentication based on handwriting using secure sketches. In: Proc. ISPA 2009, pp. 550–555 (2009)
Somol, P., Pudil, P., Kittler, J.: Fast Branch & Bound Algorithms For Optimal Feature Selection. IEEE Transactions on Pattern Analysis and Machine Intelligence 26(7), 900–912 (2004)
Sutcu, Y., Li, Q., Memon, N.: Protecting Biometric Templates with Sketch: Theory and Practice. IEEE Trans. on Information Forensics and Security 2(3), 503–512 (2007)
Verbitskiy, E., Tuyls, P., Denteneer, D., Linnartz, J.-P.: Reliable biometric authentication with privacy protection. In: Proc. 24th Benelux Symposium on Information Theory, pp. 125–132 (2003)
Vielhauer, C.: Biometric User Authentication for IT Security: From Fundamentals to Handwriting. Springer (2006)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Makrushin, A., Scheidat, T., Vielhauer, C. (2012). Improving Reliability of Biometric Hash Generation through the Selection of Dynamic Handwriting Features. In: Shi, Y.Q., Katzenbeisser, S. (eds) Transactions on Data Hiding and Multimedia Security VIII. Lecture Notes in Computer Science, vol 7228. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-31971-6_2
Download citation
DOI: https://doi.org/10.1007/978-3-642-31971-6_2
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-31970-9
Online ISBN: 978-3-642-31971-6
eBook Packages: Computer ScienceComputer Science (R0)