Sparse Representation for Ear Biometrics
In this paper we address for the first time, the problem of user identification using ear biometrics in the context of sparse representation. During the training session the compressed ear images are transformed to vectors to develop a dictionary matrix A . The downsampled probe vector y is used to develop a linear, underdetermined system of equation y = Ax, x being unknown. The ill-posed system is regularized by utilizing the sparse nature of x and the inverse problem is solved through the l 1-norm minimization. Ideally the nonzero entries in the recovered vector x correspond to the class of the probe y. The developed system does not assume any preprocessing or normalization of the ear region. We did extensive experiments on the UND [2,3] and the FEUD  databases with session variability and incorporating different head rotations and lighting conditions. The proposed system is found to be robust under varying light and head rotations yielding a high recognition rate of the order of 98%. Moreover, in context of sparse representation a tuning parameter of the system is identified and is designated as an Operating Point (OP). The significance of the OP is highlighted by mathematical arguments and experimental verifications.
KeywordsOperating Point Smart Card Sparse Representation Nonzero Entry Head Rotation
Unable to display preview. Download preview PDF.
- 1.Wright, J., Yang, A., Ganesh, A., Sastri, S.S., Ma, Y.: Robust face recognition via sparse representation. IEEE Trans. PAMI (2008) Google Scholar
- 2.Flynn, P.J., Bowyer, K.W., Phillips, P.J.: Assessment of time dependency in face recognition: An initial study. Audio- and Video-Based Biometric Person Authentication, 44–51 (2003)Google Scholar
- 4.Lu, L., Zhang, X., Zhao, Y., Jia, Y.: Ear recognition based on statistical shape model. In: International Conference on Innovative Computing Information and Control (ICICIC 2006) (2006)Google Scholar
- 6.Iannarelli, A.: Ear identification. Paramount Publishing Company, Freemont (1989)Google Scholar
- 7.Hurley, D.J., Arbab-Zavar, B., Nixon, M.S.:The ear as a biometric. In: Handbook of Biometrics (2007) Google Scholar
- 8.Moreno, B., Sanchez, A.: On the use of outer ear images for personal identification in security applications. In: Proc. IEEE 33rd Annual Intl. Conf. on Security Technology, pp. 469–476 (1999)Google Scholar
- 9.Iwano, K., Hirose, T., Kamibayashi, E., Furui, S.: Audio-visual person authentication using speech and ear images. In: Proc. of Workshop on Multimodal User Authentication, pp. 85–90 (2003)Google Scholar
- 10.Arbab-Zavar, B., Nixon, M.S., Hurley, D.J.: On model-based analysis of ear biomtrics. In: IEEE Intl. Conf. on Biometrics: Theory, Applications and Systems (September 2007) Google Scholar
- 11.Baraniuk, R.: Compressive sensing. IEEE Signal Processing Magazine 24 (2007)Google Scholar
- 14.Baraniuk, R., Davenport, M., DeVore, R., Wakin, M.B.: The johnson-lindenstrauss lemma meets compressed sensing (2006), dsp.rice.edu/cs/jlcs-v03.pdf