Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2013 Sep 12:2013:981840.
doi: 10.1155/2013/981840. eCollection 2013.

Semisupervised kernel marginal Fisher analysis for face recognition

Ziqiang Wang  1 , Xia Sun, Lijun Sun, Yuchun Huang
Affiliations

Semisupervised kernel marginal Fisher analysis for face recognition

Ziqiang Wang et al. ScientificWorldJournal. .

Abstract

Dimensionality reduction is a key problem in face recognition due to the high-dimensionality of face image. To effectively cope with this problem, a novel dimensionality reduction algorithm called semisupervised kernel marginal Fisher analysis (SKMFA) for face recognition is proposed in this paper. SKMFA can make use of both labelled and unlabeled samples to learn the projection matrix for nonlinear dimensionality reduction. Meanwhile, it can successfully avoid the singularity problem by not calculating the matrix inverse. In addition, in order to make the nonlinear structure captured by the data-dependent kernel consistent with the intrinsic manifold structure, a manifold adaptive nonparameter kernel is incorporated into the learning process of SKMFA. Experimental results on three face image databases demonstrate the effectiveness of our proposed algorithm.

PubMed Disclaimer

Figures

Figure 1
Figure 1
Face image examples of the Yale database.
Figure 2
Figure 2
Face image examples of the ORL database.
Figure 3
Figure 3
Face image examples of the CMU PIE database.
Figure 4
Figure 4
Two labelled data for training on the Yale database.
Figure 5
Figure 5
Four labelled data for training on the Yale database.
Figure 6
Figure 6
Two labelled data for training on the ORL database.
Figure 7
Figure 7
Four labelled data for training on the ORL database.
Figure 8
Figure 8
Two labelled data for training on the CMU PIE database.
Figure 9
Figure 9
Four labelled data for training on the CMU PIE database.
Figure 10
Figure 10
The performance of SKMFA varies with the parameter τ on the Yale database.
Figure 11
Figure 11
The performance of SKMFA varies with the parameter τ on the ORL database.
Figure 12
Figure 12
The performance of SKMFA varies with the parameter τ on the CMU PIE database.
See this image and copyright information in PMC

References

    1. Duda RO, Hart PE, Stork DG. Pattern Classification. 2nd edition. Hoboken, NJ, USA: Wiley-Interscience; 2000.
    1. Liu Q, Lu H, Ma S. Improving kernel fisher discriminant analysis for face recognition. IEEE Transactions on Circuits and Systems for Video Technology. 2004;14(1):42–49.
    1. Cardoso J-F. Blind signal separation: statistical principles. Proceedings of the IEEE. 1998;86(10):2009–2025.
    1. Sharkas M, Elenien MA. Eigenfaces vs. fisherfaces vs. ica for Face recognition; a comparative study. Proceedings of the 9th International Conference on Signal Processing (ICSP '08); October 2008; Beijing, China. pp. 914–919.
    1. Lee DD, Seung HS. Algorithms for nonnegative matrix factorization. Advances in Neural Information Processing Systems. 2000:556–562.

Publication types

LinkOut - more resources