CINXE.COM
{"title":"Rotation Invariant Face Recognition Based on Hybrid LPT\/DCT Features","authors":"Rehab F. Abdel-Kader, Rabab M. Ramadan, Rawya Y. Rizk","volume":20,"journal":"International Journal of Electrical and Computer Engineering","pagesStart":1613,"pagesEnd":1619,"ISSN":"1307-6892","URL":"https:\/\/publications.waset.org\/pdf\/11753","abstract":"The recognition of human faces, especially those with\r\ndifferent orientations is a challenging and important problem in image\r\nanalysis and classification. This paper proposes an effective scheme\r\nfor rotation invariant face recognition using Log-Polar Transform and\r\nDiscrete Cosine Transform combined features. The rotation invariant\r\nfeature extraction for a given face image involves applying the logpolar\r\ntransform to eliminate the rotation effect and to produce a row\r\nshifted log-polar image. The discrete cosine transform is then applied\r\nto eliminate the row shift effect and to generate the low-dimensional\r\nfeature vector. A PSO-based feature selection algorithm is utilized to\r\nsearch the feature vector space for the optimal feature subset.\r\nEvolution is driven by a fitness function defined in terms of\r\nmaximizing the between-class separation (scatter index).\r\nExperimental results, based on the ORL face database using testing\r\ndata sets for images with different orientations; show that the\r\nproposed system outperforms other face recognition methods. The\r\noverall recognition rate for the rotated test images being 97%,\r\ndemonstrating that the extracted feature vector is an effective rotation\r\ninvariant feature set with minimal set of selected features.","references":"[1] W. Zhao, R. Chellappa, P. J. Phillips, and A. Rosenfeld, \"Face\r\nRecognition: A Literature Survey,\" ACM Computing Surveys, vol. 35,\r\nno. 4, pp. 399-458, 2003.\r\n[2] R. Brunelli and T. Poggio, \"Face Recognition: Features versus\r\nTemplates,\" IEEE Trans. Pattern Analysis and Machine Intelligence,\r\nvol. 15, no. 10, pp. 1042-1052, 1993.\r\n[3] M. A. Turk and A. P. Pentland, \"Face Recognition using Eigenfaces,\"\r\nProc. of IEEE Conference on Computer Vision and Pattern\r\nRecognition, pp. 586-591, June 1991.\r\n[4] X. Yi-qiong, L. Bi-cheng and W. Bo, \"Face Recognition by Fast\r\nIndependent Component Analysis and Genetic Algorithm,\" Proc. of\r\nthe 4th International Conference on Computer and Information\r\nTechnology (CIT-04), pp. 194-198, Sept. 2004.\r\n[5] K. Nakamura, and S. Miyamoto, \"Rotation, size and shape recognition by\r\na spreading associative neural network,\" IEICE Trance. on Information\r\nand Systems, vol.E-84-D, no.8, pp.1075-1084, 2001.\r\n[6] K. Nakamura, K. Arimura, and T. Yoshikawa, \"Recognition of Object\r\nOrientation and Shape by a Rotation Spreading Associative Neural\r\nNetwork,\" Proc. IEEE-INNS Int. Joint Conf. on Neural Networks\r\n(JCNN2001), pp.565-570, 2001.\r\n[7] H. El-Bakry, \"A Rotation Invariant Algorithm for Recognition,\" Fuzzy\r\nDays 2001, LNCS 2206, pp. 284-290, 2001. Springer-Verlag Berlin\r\nHeidelberg 2001.\r\n[8] H. R. Wilson, D. Levi, L. Maffei, J. Rovamo, and R. DeValois, \"The\r\nPerception of Form: Retina to Striate Cortex\", Visual Perception: The\r\nNeurophisiologcal Foundations, Academic Press, 1990.\r\n[9] S. Chien, and I. Choi, \"Face and Facial Landmarks location based\r\nonLog-Polar Mapping\", Lecture Notes in Computer Science - LNCS\r\n1811, pp. 379-386, 2000.\r\n[10] S. Minut, S. Mahadevan, J. Henderson, and F. Dyer, \"Face Recognition\r\nusing Foveal Vision\", Lecture Notes in Computer Science - LNCS\r\n1811, pp. 424-433, 2000.\r\n[11] M. Tistarelli, and E. Grosso, \"Active Vision-Based Face\r\nAuthentication\", Image and Vision Computing, no. 18, pp. 299-314,\r\n2000.\r\n[12] A. S. Samra, S. E. Gad Allah, R. M. Ibrahim, \"Face Recognition Using\r\nWavelet Transform, Fast Fourier Transform and Discrete Cosine\r\nTransform,\" Proc. 46th IEEE International Midwest Symp. Circuits and\r\nSystems (MWSCAS'03), vol. 1, pp. 272- 275, 2003.\r\n[13] Z. Yankun and L. Chongqing, \"Efficient Face Recognition Method\r\nbased on DCT and LDA,\" Journal of Systems Engineering and\r\nElectronics, vol. 15, no. 2, pp. 211-216, 2004.\r\n[14] Z. M. Hafed and M. D. Levine, \"Face Recognition Using Discrete\r\nCosine Transform, \" International Journal of Computer Vision, vol.\r\n43, no. 3, pp. 167-188. 2001.\r\n[15] F. M. Matos, L. V. Batista, and J. Poel, \"Face Recognition Using DCT\r\nCoefficients Selection,\" Proc. of the 2008 ACM Symposium on Applied\r\nComputing, (SAC-08),pp. 1753-1757, March 2008.\r\n[16] M. Yu, G. Yan, and Q.-W. Zhu, \"New Face Recognition Method Based\r\non DWT\/DCT Combined Feature Selection,\" Proc. 5th International\r\nConference on Machine Learning and Cybernetics, pp. 3233-3236,\r\nAugust 2006.\r\n[17] K. Hyun Kim, Y.-S. Chung, J.-H. Yoo, and Y. Man Ro, \"Facial Feature\r\nExtraction Based on Private Energy Map in DCT Domain,\" ETRI\r\nJournal, Volume 29, Number 2, pp. 243-245, April 2007\r\n[18] E. Kokiopoulou and P. Frossard, \"Classification-Specific Feature\r\nSampling for Face Recognition,\" Proc. IEEE 8th Workshop on\r\nMultimedia Signal Processing, pp. 20-23, 2006.\r\n[19] X. Fan and B. Verma, \"Face recognition: A New Feature Selection and\r\nClassification Technique,\" Proc. 7th Asia-Pacific Conference on\r\nComplex Systems, December 2004.\r\n[20] A. Y. Yang, J. Wright,Y. Ma, and S. S. Sastry, \" Feature Selection in\r\nFace Recognition: A Sparse Representation Perspective,\" submitted for\r\npublication, 2007.\r\n[21] R. M. Ramadan, and R. F. Abdel-Kader, \"Face Recognition Using\r\nParticle Swarm Optimization-Based Selected Features,\" In Press, 2008.\r\n[22] J. Kennedy and R. Eberhart, \"Particle swarm optimization,\" Proc. IEEE\r\nInternational Conference on Neural Networks, pp. 1942-1948, 1995.\r\n[23] J. Kennedy and R. C. Eberhart, \"A Discrete Binary Version of the\r\nParticle Swarm Algorithm\", Proc. IEEE International Conference on\r\nSystems, Man, and Cybernetics, vol. 5, pp. 4104-4108, Oct. 1997.","publisher":"World Academy of Science, Engineering and Technology","index":"Open Science Index 20, 2008"}