Abstract This paper presents a modification for robust minutiae based fingerprint verification methods that use Delaunay triangulations. The purpose of this modification is to decrease the number of comparison operations and the error rates within the matching process, by doing a full analysis of the Delaunay triangles. From this full analysis, a modified method was proposed. The identified minutiae represent nodes of a coZnnected graph composed of triangles. With this technique, the minimum angle over all triangulations is maximized, which gives local stability to the constructed structures against rotation and translation variations. Geometric thresholds and minutiae data were used to characterize the triangulations created from input and template fingerprint images. The effectiveness of the proposed modification is confirmed with calculations of False Acceptance Rate (FAR), False Rejected Rate (FRR) and Equal Error Rate (EER) over FVC2002 databases compared to other approaches results.

References

[1] Abraham J., Kwan P., and Gao J., State of the Art in Biometrics, InTech, 2011.

[2] Arens C. The Bowyer-Watson Algorithm. An Efficient Implementation in a Database Environment, Technical Report 2002.

[3] Berg M., Cheong O., Kreveld M., and Overmars M., Computational Geometry-Algorithms and Applications, Springer-Verlag, 2008.

[4] Cappelli R., Maio D., Maltoni D., and Jain A., Performance Evaluation of Fingerprint Verification Systems, Journal of IEEE Transaction Pattern Analysis and Machine Intelligence, vol. 28, no. 1, pp. 3-18, 2006.

[5] Deng H. and Huo Q., Minutiae Matching Based Fingerprint Verification Using Delaunay Triangulation and Aligned-Edge-Guided Triangle Matching, in Proceeding of Audio and Video Based Biometric Person Authentication, New York, pp. 270-278, 2005.

[6] Imamverdiyev Y., Teoh A., and Kim J., Biometric Cryptosystem based on Discretized Fingerprint Texture Descriptors, Journal of Expert Systems with Applications, vol. 40, no. 5, pp. 1888-1901, 2013.

[7] Jin A., Ling D., and Song O., An Efficient Fingerprint Verification System using Integrated Wavelet and Fourier-Melling Invariant Transform, Journal of Image and Vision Computing, vol. 22, no. 6, pp. 503-513, 2004.

[8] Khalil M., Mohamad D., Khan M., and Al- Nuzaili Q., Fingerprint Verification using Statistical Descriptors, Journal of Digital Signal Processing, vol. 20, no. 4, pp. 1264-1273, 2009.

[9] Liu N., Yin Y., and Zhang H., A Fingerprint Matching Algorithm Based on Delaunay Triangulation Net, in Proceedings of the 5th International Conference on Computer and Information Technology, Shanghai, pp. 591-595, 2005.

[10] Maltoni D., Maio D., Jain A., and Prabhakar S., Handbook of Fingerprint Recognition, Springer-Velag, 2009.

[11] Parziale G. and Niel A., A Fingerprint Matching Using Minutiae Triangulation, Springer-Verlag, 2004.

[12] Ross A., Jain A., and Reisman J., A Hybrid Fingerprint Matcher, Journal of Pattern Recognition, vol. 36, no. 7, pp. 1661-1673, 2003.

[13] Sadeghi M., Maghooli K., and Moein M., Using Artificial Immunity Network for Face Verification, The International Arab Journal of information Technology, vol. 11, no. 4, pp. 354- 361, 2014.

[14] Yang W., Hu J., and Wang S., A Delaunay Triangle-Based Fuzzy Extractor for Fingerprint Authentication, in Proceeding of IEEE 11th International Conference on Trust, Security and Privacy in Computing and Communications, Liverpool, pp. 66-70, 2012.

[15] Yang J. and Park D., A Fingerprint Verification Algorithm using Tessellated Invariant Moment Features, Journal of Neurocomputing, vol. 71, no. 10-12, pp. 1939-1964, 2008. 354 The International Arab Journal of Information Technology, Vol. 14, No. 3, May 2017 Manuel Flores received the title of Engineer in Telecommunications and Electronic Systems with honorific mention from Instituto Tecnol gico y de Estudios Superiores de Monterrey, Campus Ciudad de M xico in 2010. In 2012, he studied the specialization in Informatics Security and Information Technologies at Instituto Polit cnico Nacional, ESIME Culhuacan. Nowadays, he is studying the master s degree in Engineering in Informatics and Information Security in the same University where he studied his specialization degree. His areas of knowledge are: electronic voting process, Secure cryptographic applications and biometry. Gualberto Torres received the title of Master in Science of Engineering in Microelectronics and Doctor in Communications and Electronics in 2004 and 2008 respectively at Instituto Polit cnico Nacional. In 2005, received the award for best master s degree thesis at IPN. He belongs to the National System of Researches in Mexico. His areas of knowledge are: Signal processing, pattern recognition, neural networks and biometry. Gina Garc a received the title of Engineer in Computation, the master s degree and Doctorate in Science at Instituto Polit cnico Nacional, ESIME Culhuacan in 2002, 2005 and 2011 respectively. During the summer in 2011, she made a postdoctoral stay in Yale University in the United States. Nowadays, she is professor at ESIME Culhuacan University in the section of Estudios de Posgrado e Investigaci n. Also, she belongs to the National System of Researchers in Mexico. Her areas of knowledge are: e-voting, design of secure cryptographic applications, information systems and cryptogaphy. Miguel Licona received the title of Mechanic Engineer from Escuela Superior de Ingenier a Mec nica y El ctrica del Instituto Polit cnico Nacional in 1973. He took a diploma course about Didactics in Mathematics at INSA in Lyon France (2007). Later, he got the master s degree in Administration and Education Development from Universidad Tecnol gica de M xico in 2008. In 2010 he studied the Doctorate in Education at Alcal University, completing 100% of the credits. His areas of knowledge are: development and investigation in didactics of mathematics with application in informatics security.