Through Biometric Card in Romania: Person Identification by Face, Fingerprint and Voice Recognition

Authors: Hariton N. Costin, Iulian Ciocoiu, Tudor Barbu, Cristian Rotariu

Abstract:

In this paper three different approaches for person verification and identification, i.e. by means of fingerprints, face and voice recognition, are studied. Face recognition uses parts-based representation methods and a manifold learning approach. The assessment criterion is recognition accuracy. The techniques under investigation are: a) Local Non-negative Matrix Factorization (LNMF); b) Independent Components Analysis (ICA); c) NMF with sparse constraints (NMFsc); d) Locality Preserving Projections (Laplacianfaces). Fingerprint detection was approached by classical minutiae (small graphical patterns) matching through image segmentation by using a structural approach and a neural network as decision block. As to voice / speaker recognition, melodic cepstral and delta delta mel cepstral analysis were used as main methods, in order to construct a supervised speaker-dependent voice recognition system. The final decision (e.g. “accept-reject" for a verification task) is taken by using a majority voting technique applied to the three biometrics. The preliminary results, obtained for medium databases of fingerprints, faces and voice recordings, indicate the feasibility of our study and an overall recognition precision (about 92%) permitting the utilization of our system for a future complex biometric card.

Keywords: Biometry, image processing, pattern recognition, speech analysis.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1071630

References:

[1] Barbu, T. Discrete speech recognition using a Hausdorff-based metric. In Proc. of the 1st Int. Conf. of E-Business and Telecomm. Networks, ICETE 2004, Setubal, Portugal, Vol. 3, (Aug. 2004), pp.363-368.
[2] Barbu, T. Modelarea Sistemelor Informatice Multimedia (Modeling of Multimedia Informatic Systems). Editura Academiei Române, 2006.
[3] Bartlett, M.S., Movellan, J.R., Sejnowski, T.R.. Face recognition by independent component analysis. IEEE Trans. on Neural Networks, 13, (2002), pp. 1450-1464.
[4] Belkin, M., Niyogi, P. Laplacian eigenmaps for dimensionality reduction and data representation. Neural Computation, 15, (2003), 1373-1396.
[5] Brunelli, R., Poggio, T. Face recognition: features versus templates. IEEE Trans. Pattern Anal. Machine Intell. 15, (1993), 1042-1052.
[6] Costin, H., et al. Fingerprint identification system using neural network approach, în Advances in Modeling and Analysis,B,36,No.2,(1995),21- 27.
[7] Costin, M., Barbu, T., Zbancioc, M., Grichnik, A. Automatic speaker recognition: inference of new decision tools. Journal of Fuzzy Systems and Artificial Intelligence, Romanian Academy, 2005.
[8] Donoho, D., Sodden, V. When does non-negative matrix factorization give a correct decomposition into parts? In: Proc. Neural Inform. Process. Syst. (2003).
[9] Edwards, G.J., Taylor, C.J., Cootes, T. Face recognition using the active appearance model. In: Proc. European Conf. on Computer Vision, (1998), pp. 581-595.
[10] Furui, S. Speaker-independent isolated word recognition using dynamic features of the speech spectrum, IEEE Transactions on Acoustic Speech and Signal Processing, (1986), Vol ASSP-34, No.1, pp. 52-59.
[11] Guillamet, D., Vitrià, J. Classifying faces with non-negative matrix factorization. In: Proc. 5th Catalan Conf. for Artif. Intell., (2002), pp.24- 31.
[12] He X., Niyogi, P., 2003. Locality preserving projections. In: Proc. Neural Inform. Process. Syst. 16, Canada.
[13] He, X., Yan, S., Hu, Y., Niyogi, P., Zhang, H.J. Face recognition using Laplacianfaces. IEEE Trans. P A M I, 27, (2005), 328-340.
[14] Hoyer, P.O. Non-negative matrix factorization with sparseness constraints. Journal of Machine Learning Research 5, (2004), 1457- 1469.
[15] Hrechak, A., McHugh, J. Automated fingerprint recognition using structural matching, Pattern Recognition, 23, no. 8, (1990), pp. 893-904.
[16] Khotanzad, A., Hong, Y.H. Rotation invariant image recognition using features selected via a systematic method, Pattern Recognition, vol. 23, no. 10, (1990), pp. 1089-1101.
[17] Lam, L. et al. Thinning methodologies - a comprehensive survey, IEEE Trans. on PAMI-14, 9, (1992), pp. 869-885.
[18] Lee, D.D., Seung, H.S. Learning the parts of objects by non-negative matrix factorization. Nature 401, (1999), pp. 788-791.
[19] Li, S.Z., Hou, X.W., Zhang, H.J. Learning spatially localized, partsbased representation. In: Proc. IEEE Internat. Conf. on Computer Vision and Pattern Recognition, (2001).
[20] Logan B. Mel frequency cepstral coefficients for music modelling, In Proc Int. Symp. on Music Information Retrieval (ISIMIR). Plymouth, MA, 2000.
[21] Maltoni, D., et al. Handbook of Fingerprint Recognition, Springer, (2003).
[22] Penev, P., Atick, J. Local feature analysis: a general statistical theory for object representation. Network: Comput. in Neural Syst.,7,(1996),477- 500.
[23] Srinivasan, V.S., Murthy, Neural network detection of singular points in fingerprint images, Pattern Recognition, 25, no. 2, (1992), pp. 139-153.
[24] Wiskott, L., Fellous, J.M., Kruger, N., v.d. Malsburg, C. Face recognition by elastic graph matching. IEEE Trans. Pattern Anal. Machine Intell. 19, (1997), pp. 775-779.
[25] Xiao, Q., Raafat, H. Fingerprint image postprocessing: a combined statistical and structural approach, Pattern Recognition, vol. 24, no. 10, (1991), pp. 985-992.