Abstract
In this paper, we systematically study the effect of poorly registered faces on the training and inferring stages of traditional face recognition algorithms. We then propose a novel multiple-instance based subspace learning scheme for face recognition. In this approach, we iteratively update the subspace training instances according to diverse densities, using class-balanced supervised clustering. We test our multiple instance subspace learning algorithm with Fisherface for the application of face recognition. Experimental results show that the proposed learning algorithm can improve the robustness of current methods with poorly aligned training and testing data.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Wiskott, L., Fellous, J.M., Krüger, N., von der Malsburg, C.: Face recognition by elastic bunch graph matching. In: Sommer, G., Daniilidis, K., Pauli, J. (eds.) CAIP 1997. LNCS, vol. 1296, pp. 456–463. Springer, Heidelberg (1997)
Kirby, M., Sirovich, L.: Application of the karhunen-loeve procedure for the characterization of human faces. IEEE Transactions on Pattern Analysis and Machine Intelligence 12(1), 103–108 (1990)
Turk, M., Pentland, A.: Face recognition using eigenfaces. In: Proceedings of IEEE Computer Vision and Pattern Recognition, pp. 586–591. IEEE Computer Society Press, Los Alamitos (1991)
Belhumeur, P.N., Hespanha, J., Kriegman, D.J.: Eigenfaces vs. fisherfaces: Recognition using class specific linear projection. IEEE Transactions on Pattern Analysis and Machine Intelligence 19(7), 711–720 (1997)
Etemad, K., Chellappa, R.: Discriminant analysis for recognition of human face images. In: Bigün, J., Borgefors, G., Chollet, G. (eds.) AVBPA 1997. LNCS, vol. 1206, pp. 127–142. Springer, Heidelberg (1997)
Phillips, P.J., 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)
Martinez, A.: Recognizing imprecisely localized, partially occuded and expression variant faces from a single sample per class. IEEE Transactions on Pattern Analysis and Machine Intelligence 24(6), 748–763 (2002)
Shan, S., Chang, Y., Gao, W., Cao, B.: Curse of mis-alignment in face recognition: Problem and a novel mis-alignment learning solution. In: Proceedings of International Conference on Automatic Face and Gesture Recognition, pp. 314–320 (2004)
Viola, P., Platt, J.C, Zhang, C.: Multiple instance boosting for object dection. In: Proceedings of Neural Information Processing Systems (2005)
Maron, O., Lozano-Perez, T.: A framework for multiple-instance learning. In: Proceedings of Neural Information Processing Systems, pp. 570–576 (1998)
Andrews, S., Tsochantaridis, I., Hofmann, T.: Support vecctor machines for multiple-instance learning. In: Proceedings of Neural Information Processing Systems, pp. 561–568 (2002)
Wang, J., Zucker, J.D.: Solving multiple-instance problem: A lazy learning approach. In: Proceedings of International Conference on Machine Learning, pp. 1119–1125 (2000)
Blum, C., Blesa, M.J.: New metaheuristic approaches for the edge-weighted k-cardinality tree problem. Computers and Operations Research 32(6), 1355–1377 (2005)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Li, Z., Liu, Q., Metaxas, D. (2007). Face Mis-alignment Analysis by Multiple-Instance Subspace. In: Yagi, Y., Kang, S.B., Kweon, I.S., Zha, H. (eds) Computer Vision – ACCV 2007. ACCV 2007. Lecture Notes in Computer Science, vol 4844. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-76390-1_88
Download citation
DOI: https://doi.org/10.1007/978-3-540-76390-1_88
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-76389-5
Online ISBN: 978-3-540-76390-1
eBook Packages: Computer ScienceComputer Science (R0)