Abstract
We propose a novel method using a perfectly local facial representation based on ICA. We named our method ”LS-ICA method”. In the LS-ICA method, basis images are made from their corresponding ICA basis images simply by removing non-salient regions. The LS-ICA basis images display perfectly local characteristics because they contain only locally salient feature regions. This enables us to effectively realize the idea of ”recognition by parts” for face recognition. Experimental results using AT&T, Harvard, FERET and AR databases show that the recognition performance of the LS-ICA method outperforms that of PCA and ICA methods especially in the cases of facial images that have partial occlusions and local distortions such as changes in facial expression and at low dimensions.
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
Back, K., Draper, B.A., Beveridge, J.R., She, K.: PCA vs ICA: A comparison on the FERET data set. In: Joint Conference on Information Sciences, Durham, N.C. (2002)
Turk, M.A., Pentland, A.P.: Eigenfaces for recognition. Cognitive Neuroscience 3(1), 71–86 (1991)
Bartlett, M.S., Movellan, J.R., Sejnowski, T.J.: Face Recognition by Independent Component Analysis. IEEE Transaction on Neural Networks 13, 1450–1464 (2002)
Hyvarinen, A., Oja, E.: Independent component analysis: a tutorial (1999), http://www.cis.hut.fi/~aapo/papers/IJCNN99_tutorialweb/
Cardoso, J.F.: Infomax and Maximum Likelihood for Source Separation. IEEE Letters on Signal Processing 4, 112–114 (1997)
Phillips, P.J., Moon, H., Rizvi, S.A., Rauss, P.J.: The FERET Evaluation Methodology for Face Recognition Algorithms. Pattern Analysis and Machine Intelligence 22, 1090–1104 (2000)
Martinez, M., Benavente, R.: The AR face database. CVC Tech. Report #24 (1998)
Bartlett, M.S.: Face Image Analysis by Unsupervised Learning. Foreword by T. J. Sejnowski, Kluwer International Series on Engineering and Computer Science. Kluwer Academic Publishers, Boston (2001)
Pentland, P.: Recognition by parts. In: IEEE Proceedings of the First International Conference on Computer Vision, pp. 612–620 (1987)
Lee, D.D., Seung, H.S.: Learning the parts of objects by non-negative matrix factorization. Nature 401, 788–791 (1999)
Bell, J., Sejnowski, T.J.: The independent components of natural scenes are edge filters. Advance in Neural Information Processing Systems 9 (1997)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kim, J., Choi, J., Yi, J. (2004). ICA Based Face Recognition Robust to Partial Occlusions and Local Distortions. In: Zhang, D., Jain, A.K. (eds) Biometric Authentication. ICBA 2004. Lecture Notes in Computer Science, vol 3072. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-25948-0_21
Download citation
DOI: https://doi.org/10.1007/978-3-540-25948-0_21
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-22146-3
Online ISBN: 978-3-540-25948-0
eBook Packages: Springer Book Archive