Abstract
In this paper we propose a new tensor based analysis algorithm for face gender recognition, in which we consider the different feature structures of male/female images respectively. Given a gender labeled face dataset, we aim to obtain their meaningful low-dimensional data representation which preserves their intrinsic male/female structures, and this is achieved by combining tensor analysis with a local geometric preserving constraint on the tensor decomposition. In the proposed approach, a similarity graph is built to represent images of the same gender and separate those of different genders. Technically, a 5-mode (w.r.t gender, pose, illumination, expression, pixels) tensor decomposition is used to analyze the packed image matrix, which is constrained on the proposed graph and this graph can preserve as much as possible on the information of gender in the decomposed component data. The objective of gender recognition is formulated as an optimization problem and then solved by an alternating algorithm. Finally, experiments are implemented on several face databases and it is proved that the proposed approach can enhance gender discriminant capability significantly compared to the tensor approach, while has already achieved a comparable recognition performance as a state-of-art algorithm.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Cottrell, G.W., Metcalfe, J.: Empath: face, emotion, and gender recognition using holons. In: NIPS-3: Proceedings of the 1990 conference on Advances in neural information processing systems, vol. 3, pp. 564–571. Morgan Kaufmann Publishers Inc., San Francisco (1990)
Bruce, V., Burton, A.M., Hanna, E., Healey, P., Mason, O., Coombes, A., Fright, R., Linney, A.: Sex discrimination: how do we tell the difference between male and female faces? Perception 22, 131–152 (1993)
Tamura, S., Kawai, H., Mitsumoto, H.: Male/female identification from 8×6 very low resolution face images by neural network. Pattern Recognition 29(2), 331–335 (1996)
Makinen, E., Raisamo, R.: Evaluation of gender classification methods with automatically detected and aligned faces. IEEE Trans. Pattern Anal. Mach. Intell. 30(3), 541–547 (2008)
Yang, Z., Li, M., Ai, H.: An experimental study on automatic face gender classification. In: International Conference on Pattern Recognition, vol. 3, pp. 1099–1102 (2006)
Kawano, T., Kato, K., Yamamoto, K.: A comparison of the gender differentiation capability between facial parts. In: Proceedings of 17th International Conference on Pattern Recognition (ICPR 2004), Washington, DC, USA, vol. 1, pp. 350–353. IEEE Computer Society, Los Alamitos (2004)
Moghaddam, B., Yang, M.H.: Gender classification with support vector machines. In: Proc. of Int’l Conf. on Automatic Face and Gesture Recognition (FG 2000), Grenoble, France, March 2000, pp. 306–311 (2000)
Yan, S., Xu, D., Zhang, B., Zhang, H.J., Yang, Q., Lin, S.: Graph embedding and extensions: A general framework for dimensionality reduction. IEEE Transactions on Pattern Analysis and Machine Intelligence 29(1), 40–51 (2007)
Xu, D., Yan, S., Tao, D., Lin, S., Zhang, H.J.: Marginal fisher analysis and its variants for human gait recognition and content- based image retrieval. IEEE Transactions on Image Processing 16(11), 2811–2821 (2007)
Vasilescu, M.A.O., Terzopoulos, D.: Multilinear analysis of image ensembles: Tensorfaces. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2350, pp. 447–460. Springer, Heidelberg (2002)
Vasilescu, M.A.O., Terzopoulos, D.: Multilinear image analysis for facial recognition. In: ICPR (2), pp. 511–514 (2002)
Bader, B.W., Kolda, T.G.: Matlab tensor toolbox version 2.2 (January 2007), http://csmr.ca.sandia.gov/~tgkolda/tensortoolbox/
Georghiades, A., Belhumeur, P., Kriegman, D.: From few to many: Illumination cone models for face recognition under variable lighting and pose. IEEE Trans. Pattern Anal. Mach. Intelligence 23(6), 643–660 (2001)
Lee, K., Ho, J., Kriegman, D.: Acquiring linear subspaces for face recognition under variable lighting. IEEE Trans. Pattern Anal. Mach. Intelligence 27(5), 684–698 (2005)
Phillips, J.P., Moon, H., Rizvi, S.A., Rauss, P.J.: The feret evaluation methodology for face-recognition algorithms. IEEE Transactions on Pattern Analysis and Machine Intelligence 22(10), 1090–1104 (2000)
Rana, S., Liu, W., Lazarescu, M., Venkatesh, S.: Recognising faces in unseen modes: A tensor based approach. In: CVPR (2008)
Rana, S., Liu, W., Lazarescu, M., Venkatesh, S.: Efficient tensor based face recognition. In: ICPR, pp. 1–4 (2008)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Qiu, H., Liu, Wq., Lai, JH. (2010). Gender Recognition via Locality Preserving Tensor Analysis on Face Images. In: Zha, H., Taniguchi, Ri., Maybank, S. (eds) Computer Vision – ACCV 2009. ACCV 2009. Lecture Notes in Computer Science, vol 5996. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-12297-2_58
Download citation
DOI: https://doi.org/10.1007/978-3-642-12297-2_58
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-12296-5
Online ISBN: 978-3-642-12297-2
eBook Packages: Computer ScienceComputer Science (R0)