Abstract
In this paper, we proposed a new linear regression-based approach for face recognition, called farthest subspace classification. In previous literatures, it was believed that the facial images from a specific object class tend to lie on a linear subspace, i.e. the class-specific subspace. Therefore a query image will be considered belonging to its nearest subspace (NS) of a class. The distance from a query image to each class-specific subspace is calculated simply by the linear regression. In this paper, we proposed a novel notion of face recognition that in the complete feature space spanned by all the gallery images, each class-specific subspace has not only common subspace shared by every class-specific subspace, but also its unique coordinate bases, which are available discriminative information. Based on this notion, we develop farthest subspace (FS) classifier to perform face recognition. The experimental results supported the proposed novel concept. Furthermore, we proposed nearest-farthest subspace (NFS) classification using both NS and FS rules, which outperform NS used alone.
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.
Similar content being viewed by others
References
Cover, T.M., Hart, P.E.: Nearest Neighbor Pattern Classification. IEEE Trans. Information Theory 13, 21–27 (1967)
Li, S., Lu, J.: Face Recognition Using Nearest Feature Line. IEEE Trans. Neural Networks 10, 439–443 (1999)
Chien, J., Wu, C.: Discriminant Waveletfaces and Nearest Feature Classifiers for Face Recognition. IEEE Trans. Pattern Analysis and Machine Intelligence 24, 1644–1649 (2002)
Naseem, I., Togneri, R., Bennamoun, M.: Linear Regression for Face Recognition. IEEE Trans. Pattern Analysis and Machine Intelligence 32, 2106–2112 (2010)
Wright, J., Yang, A.Y., Ganesh, A., Sastry, S.S., Ma, Y.: Robust Face Recognition via Sparse Representation. IEEE Trans. Pattern Analysis and Machine Intelligence 31, 210–227 (2009)
Belhumeur, P., Hespanha, J., Kriegman, D.: Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection. IEEE Trans. Pattern Analysis and Machine Intelligence 19, 711–720 (1997)
Lee, K.C., Ho, J., Kriegman, D.: Acquiring Linear Subspaces for Face Recognition under Variable Lighting. IEEE Trans. Pattern Analysis and Machine Intelligence 27, 684–698 (2005)
Samaria, F., Harter, A.: Parameterisation of a Stochastic Model for Human Face Identification. In: Proc. Second IEEE Workshop Applications of Computer Vision (1994)
Georgia Tech Face Database, http://www.anefian.com/face_reco.htm
Barsi, R., Jacobs, D.: Lambertian Reflection and Linear Subspaces. IEEE Trans. Pattern Analysis and Machine Intelligence 25, 218–233 (2003)
Xu, Y., Zhang, D., Yang, J.Y.: A Feature Extraction Method for Use with Bimodal Biometics. Pattern Recognition 43, 1106–1115 (2010)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Mi, JX. (2012). A New Subspace Approach for Face Recognition. In: Huang, DS., Gan, Y., Premaratne, P., Han, K. (eds) Bio-Inspired Computing and Applications. ICIC 2011. Lecture Notes in Computer Science(), vol 6840. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-24553-4_73
Download citation
DOI: https://doi.org/10.1007/978-3-642-24553-4_73
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-24552-7
Online ISBN: 978-3-642-24553-4
eBook Packages: Computer ScienceComputer Science (R0)