Abstract
Face recognition from a single image remains an important task in many practical applications and a significant research challenge. Some of the challenges are inherent to the problem, for example due to changing lighting conditions. Others, no less significant, are of a practical nature – face recognition algorithms cannot be assumed to operate on perfect data, but rather often on data that has already been subject to pre-processing errors (e.g. localization and registration errors). This paper introduces a novel method for face recognition that is both trained and queried using only a single image per subject. The key concept, motivated by abundant prior work on face appearance manifolds, is that of face part manifolds – it is shown that the appearance seen through a sliding window overlaid over an image of a face, traces a trajectory over a 2D manifold embedded in the image space. We present a theoretical argument for the use of this representation and demonstrate how it can be effectively exploited in the single image based recognition. It is shown that while inheriting the advantages of local feature methods, it also implicitly captures the geometric relationship between discriminative facial features and is naturally robust to face localization errors. Our theoretical arguments are verified in an experimental evaluation on the Yale Face Database.
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
Lui, Y.M., Beveridge, J.R.: Grassmann registration manifolds for face recognition, vol. 2, pp. 44–57 (2008)
Mita, T., Kaneko, T., Stenger, B., Hori, O.: Discriminative feature co-occurrence selection for object detection. PAMI 30(7), 1257–1269 (2008)
Matas, J., Bilek, P., Hamouz, M., Kittler, J.: Discriminative regions for human face detection (2002)
Sivic, J., Everingham, M., Zisserman, A.: Person spotting: video shot retrieval for face sets, pp. 226–236 (2005)
Arca, S., Campadelli, P., Lanzarotti, R.: A face recognition system based on local feature analysis. In: Kittler, J., Nixon, M.S. (eds.) AVBPA 2003. LNCS, vol. 2688, pp. 182–189. Springer, Heidelberg (2003)
Bolme, D.S.: Elastic bunch graph matching. Master’s thesis, Colorado State University (2003)
Heo, J., Abidi, B., Paik, J., Abidi, M.A.: Face recognition: Evaluation report for FaceIt®. In: Proc. International Conference on Quality Control by Artificial Vision, vol. 5132, pp. 551–558 (2003)
Stergiou, A., Pnevmatikakis, A., Polymenakos, L.: EBGM vs. subspace projection for face recognition. In: Proc. International Conference on Computer Vision Theory and Applications (2006)
Lee, K., Kriegman, D.: Online learning of probabilistic appearance manifolds for video-based recognition and tracking, vol. 1, pp. 852–859 (2005)
Arandjelović, O., Cipolla, R.: A pose-wise linear illumination manifold model for face recognition using video, vol. 113 (2008)
Sim, T., Zhang, S.: Exploring face space. In: Proc. IEEE Workshop on Face Processing in Video, p. 84 (2004)
Arandjelović, O., Cipolla, R.: Face recognition from video using the generic shape-illumination manifold, vol. 4, pp. 27–40 (2006)
Fitzgibbon, A., Zisserman, A.: On affine invariant clustering and automatic cast listing in movies, pp. 304–320 (2002)
Gao, Y., Wang, Y., Feng, X., Zhou, X.: Face recognition using most discriminative local and global features, vol. 1, pp. 351–354 (2006)
Georghiades, A.S., Belhumeur, P.N., Kriegman, D.J.: From few to many: Illumination cone models for face recognition under variable lighting and pose 23(6), 643–660 (2001)
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
Arandjelović, O. (2010). Unfolding a Face: From Singular to Manifold. 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_20
Download citation
DOI: https://doi.org/10.1007/978-3-642-12297-2_20
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)