Abstract
The SVDD (support vector data description) is one of the most well-known one-class support vector learning methods, in which one tries the strategy of utilizing balls defined on the feature space in order to distinguish a set of normal data from all other possible abnormal objects. In this paper, we consider the problem of reconstructing facial images from the partially damaged ones, and propose to use the SVDD-based de-noising for the reconstruction. In the proposed method, we deal with the shape and texture information separately. We first solve the SVDD problem for the data belonging to the given prototype facial images, and model the data region for the normal faces as the ball resulting from the SVDD problem. Next, for each damaged input facial image, we project its feature vector onto the decision boundary of the SVDD ball so that it can be tailored enough to belong to the normal region. Finally, we obtain the image of the reconstructed face by obtaining the pre-image of the projection, and then further processing with its shape and texture information. The applicability of the proposed method is illustrated via some experiments dealing with damaged facial images.
Chapter PDF
Similar content being viewed by others
References
Tax, D., Duin, R.: Support Vector Domain Description. Pattern Recognition Letters 20, 1191–1199 (1999)
Tax, D.: One-Class Classification, Ph.D. Thesis, Delft University of Technology (2001)
Hwang, B.-W., Lee, S.-W.: Reconstruction of partially damaged face images based on a morphable face model. IEEE Transactions on Pattern Analysis and Machine Intelligence 25, 365–372 (2003)
Beymer, D., Poggio, T.: Image representation for visual learning. Science 272, 1905–1909 (1996)
Vetter, T., Troje, N.E.: Separation of texture and shape in images of faces for image coding and synthesis. Journal of the Optical Society of America A 14, 2152–2161 (1997)
Blanz, V., Romdhani, S., Vetter, T.: Face identification across different poses and illuminations with a 3d morphable model. In: Proceedings of the 5th International Conference on Automatic Face and Gesture Recognition, Washington, D.C., pp. 202–207 (2002)
Kwok, J.T., Tsang, I.W.: The pre-image problem in kernel methods. IEEE Transactions on Neural Networks, 15, 1517–1525 (2004)
Jones, M.J., Sinha, P., Vetter, T., Poggio, T.: Top-down learning of low-level vision task[Brief Communication]. Current Biology 7, 991–994 (1997)
Park, J., Kang, D., Kim, J., Tsang, I.W., Kwok, J.T.: Pattern de-noising based on support vector data description. To appear in Proceedings of International Joint Conference on Neural Networks (2005)
Mika, S., Schölkopf, B., Smola, A., Müller, K.R., Scholz, M., Rätsch, G.: Kernel PCA and de-noising in feature space. In: Advances in Neural Information Processing Systems, pp. 536–542. MIT Press, Cambridge (1999)
Williams, C.K.I.: On a connection between kernel PCA and metric multidimensional scaling. Machine Learning 46, 11–19 (2002)
Cox, T.F., Cox, M.A.A.: Multidimensional Scaling, 2nd edn., London, U.K. Monographs on Statistics and Applied Probability vol. 88. Chapman & Hall, Boca Raton (2001)
Hwang, B.-W., Blanz, V., Vetter, T., Song, H.-H., Lee, S.-W.: Face Reconstruction Using a Small Set of Feature Points. In: Bülthoff, H.H., Poggio, T.A., Lee, S.-W. (eds.) BMCV 2000. LNCS, vol. 1811, pp. 308–315. Springer, Heidelberg (2000)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Park, J., Kang, D., Kwok, J.T., Lee, SW., Hwang, BW., Lee, SW. (2005). Facial Image Reconstruction by SVDD-Based Pattern De-noising. In: Zhang, D., Jain, A.K. (eds) Advances in Biometrics. ICB 2006. Lecture Notes in Computer Science, vol 3832. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11608288_18
Download citation
DOI: https://doi.org/10.1007/11608288_18
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-31111-9
Online ISBN: 978-3-540-31621-3
eBook Packages: Computer ScienceComputer Science (R0)