{"references": ["Bledsoe, W. W. The Model Method in Facial Recognition, Technical Report\nPRI 15, Panoramic Research, Inc., Palo Alto, California, 1964", "M. Kirby and L. Sirovich. Application of the Karhunen-Loeve procedure for\nthe characterization of human faces. IEEE Transactions on Pattern analysis\nand Machine Intelligence 12, 1990", "Jolliffe, I. T. Principal Component Analysis. Springer-Verlag. p. 487, 1986", "A. Pentland, T. Starner, N. Etcoff, N. Masoiu, O. Oliyide, and M. Turk.\nExperiments with Eigenfaces. Proc. Looking at People Workshop Int'l Joint\nConf. Artifical Intelligence, 1993", "McLachlan, G. J. Discriminant Analysis and Statistical Pattern Recognition.\nWiley Interscience, 2004", "Marian Stewart Bartlett, Javier R. Movellan, and Terrence J. Sejnowski Face\nRecognition by Independent Component Analysis. IEEE Trans Neural Netw.\nvol. 13(6), pages 14501464, 2002", "Laurenz Wiskott, Jean-Marc Fellous,Norbert Kruger, and Christoph von der\nMalsburg. Face Recognition by Elastic Bunch Graph Matching. Intelligent\nBiometric Techniques in Fingerprint and Face Recognition, Chapter 11, pages\n355-396, 1999", "Arnold F. Nikiforov, Vasilii B. Uvarov, Sergei K. Suslov. Classical Orthogonal\nPolynomials of a Discrete Variable. Springer Series in Computational Physics,\n1991", "Sajad Farokhi, Siti Mariyam Shamsuddin, Jan Flusser, Usman Ullah Sheikh.\nAssessment of Time-Lapse in Visible and Thermal Face Recognition. World\nAcademy of Science, Engineering and Technology Vol.6, 2012\n[10] Mukundan, R., Ong S.H., Lee P.A. Image analysis by Tchebichef moments.\nImage Processing, IEEE Transactions on, Vol.10 , Issue: 9, 2001\n[11] Yap P.T., Paramesran R., Ong S.H. Image analysis by Krawtchouk moments.\nIEEE Trans Image Process. Vol. 12, pages 1367-77, 2003\n[12] Sri dhar Dasari, Sridhar Dasari. Face Recognition using Tchebichef\nMoments.International Journal of Infromation and Network Security, Vol 1,\nNo 4, 2012\n[13] J Sheeba Rani, D Devaraj. Face recognition using Krawtchouk moment.\nSadhana, Vol. 37, Issue 4, pages 441-460, 2012 [14] Pew-Thian Yap, Paramesran, R., Seng-Huat Ong. Image Analysis Using Hahn\nMoments. Pattern Analysis and Machine Intelligence, IEEE Transactions on,\nVol. 29, Issue 11, 2007\n[15] Ferdinando Samaria, Andy Harter. Parameterisation of a Stochastic Model\nfor Human Face Identification. Proceedings of 2nd IEEE Workshop on\nApplications of Computer Vision, Sarasota FL, 1994\n[16] P. J. Flynn, K. W. Bowyer, and P. J. Phillips. Assessment of time dependency\nin face recognition: An initial study. Audio and Video-Based Biometric Person\nAuthentication, pages 44-51, 2003.\n[17] X. Chen, P. J. Flynn, and K. W. Bowyer. Visible -light and Infrared Face\nRecognition. ACM Workshop on Multimodal User Authentication, pages 48-\n55, 2003\n[18] Jan Flusser, Barbara Zitova, Tomas Suk. Moments and Moment Invariants in\nPattern Recognition. ISBN: 978-0-470-69987-4, page 6, 2009\n[19] Jian Zhou, Huazhong Shu, Hongqing Zhu, Christine Toumoulin, and Limin\nLuo. Image Analysis by Discrete Orthogonal Hahn Moments. Lecture Notes\nin Computer Science, Vol. 3656, pages 524-531, 2005\n[20] Paul Viola, Michael Jones. Robust Real-time Object Detection. International\nJournal of Computer Vision, 2001\n[21] Andrew Fitzgibbon, Maurizio Pilu, and Robert B. Fisher. Direct Least\nSquare Fitting of Ellipses. Proc. of the 13th Internation Conference on Pattern\nRecognition, pages 253257, Vienna, 1996\n[22] http://www.cl.cam.ac.uk/research/dtg/attarchive /facedatabase.html.\n[23] Sayyouri M, Hmimid A, Qjidaa H. Improving the performance of image\nclassification by Hahn moment invariants. Journal of the Optical Society of\nAmerica, Vol. 30, Issue 11, pages 2381-2394, 2013"]}

One of the most critical decision points in the design of a face recognition system is the choice of an appropriate face representation. Effective feature descriptors are expected to convey sufficient, invariant and non-redundant facial information. In this work we propose a set of Hahn moments as a new approach for feature description. Hahn moments have been widely used in image analysis due to their invariance, nonredundancy and the ability to extract features either globally and locally. To assess the applicability of Hahn moments to Face Recognition we conduct two experiments on the Olivetti Research Laboratory (ORL) database and University of Notre-Dame (UND) X1 biometric collection. Fusion of the global features along with the features from local facial regions are used as an input for the conventional k-NN classifier. The method reaches an accuracy of 93% of correctly recognized subjects for the ORL database and 94% for the UND database.