Abstract
This paper presents a novel hybrid two-directional, two-dimensional Principal Component Analysis based correlation filter for face recognition. This hybrid (2D)\(^2\)PCA-correlation filter is capable of simultaneously dealing with several uncontrolled factors that are present in video surveillance cameras making it difficult to properly recognize faces. Such factors are addressed by linking (2D)\(^2\)PCA in the Fourier domain with correlation filters (CFs) to speed up the process of video-based face recognition. The former method helps to extract and to represent more efficiently the facial features using the original image matrices, while the later method is used to simultaneously handle illumination variations, expression, partial occlusions and spatial shifts. An exploration of the capabilities of this novel method is performed using the Yale-B, AR, and YouTube face databases, showing an improvement in face recognition despite using a subspace of smaller dimensionality.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
A pre-whitening step is performed to yield a phase-only spectrum with a unity magnitude for all spatial frequencies (u, v).
References
Benitez-Garcia, G., Olivares-Mercado, J., Sanchez-Perez, G., Nakano-Miyatake, M., Perez-Meana, H.: A sub-block-based eigenphases algorithm with optimum sub-block size. Knowl. Based Syst. 37, 415–426 (2013)
Bhagavatula, R., Savvides, M.: Eigen and Fisher-Fourier spectra for shift invariant pose-tolerant face recognition. In: Singh, S., Singh, M., Apte, C., Perner, P. (eds.) ICAPR 2005. LNCS, vol. 3687, pp. 351–359. Springer, Heidelberg (2005). doi:10.1007/11552499_40
Chellappa, R., Wilson, C., Sirohey, S.: Human and machine recognition of faces: a survey. Proc. IEEE 83(5), 705–741 (1995)
Chen, S., Mau, S., Harandi, M.T., Sanderson, C., Bigdeli, A., Lovell, B.C.: Face recognition from still images to video sequences: a local-feature-based framework. J. Image Video Process. 2011, 11:1–11:14 (2011)
Hayes, M., Lim, J., Oppenheim, A.: Signal reconstruction from phase or magnitude. IEEE Trans. Acoust. Speech Signal Process. 28(6), 672–680 (1980)
Kong, H., Wang, L., Teoh, E.K., Li, X., Wang, J.G., Venkateswarlu, R.: Generalized 2D principal component analysis for face image representation and recognition. Neural Netw. 18(56), 585–594 (2005)
Vijaya Kumar, B.V.K., Savvides, M., Xie, C.: Correlation pattern recognition for face recognition. Proc. IEEE 94(11), 1963–1976 (2006)
Lee, K., Ho, J., Kriegman, D.: Acquiring linear subspaces for face recognition under variable lighting. IEEE Trans. Pattern Anal. Mach. Intell. 27(5), 684–698 (2005)
Li, Y., Savvides, M., Bhagavatula, V.: Illumination tolerant face recognition using a novel face from sketch synthesis approach and advanced correlation filters. In: IEEE International Conference on Acoustics, Speech and Signal Processing, vol. 2, p. II (2006)
Liu, X., Chen, T., Vijaya Kumar, B.V.K.: Face authentication for multiple subjects using eigenflow. Pattern Recogn. 36(2), 313–328 (2003)
Martinez, A.M., Kak, A.C.: PCA versus LDA. IEEE Trans. Pattern Anal. Mach. Intell. 23(2), 228–233 (2001)
Oppenheim, A., Lim, J.: The importance of phase in signals. Proc. IEEE 69(5), 529–541 (1981)
Ribaric, S., Maracic, M.: Eigenphase-based face recognition: a comparison of phase-information extraction methods. In: Proceedings of IEEE ERK, pp. 233–236 (2010)
Sao, A.: Combining analytic phase and Fourier phase for face recognition. In: International Conference on Image Information Processing, pp. 1–4 (2011)
Savvides, M., Vijaya Kumar, B.V.K., Khosla, P.: Eigenphases vs eigenfaces. In: 17th International Conference on Pattern Recognition, vol. 3, pp. oo810–oo813 (2004)
Savvides, M., Vijaya Kumar, B.V.K.: Illumination normalization using logarithm transforms for face authentication. In: Kittler, J., Nixon, M.S. (eds.) AVBPA 2003. LNCS, vol. 2688, pp. 549–556. Springer, Heidelberg (2003). doi:10.1007/3-540-44887-X_65
Savvides, M., Vijaya Kumar, B.V.K., Khosla, P.K.: Robust shift-invariant biometric identication from partial face images. Proc. SPIE 5404, 124–135 (2004)
Savvides, M., Vijaya Kumar, B.V.K., Khosla, P.K.: “Corefaces” - robust shift invariant PCA based correlation filter for illumination tolerant face recognition. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2, pp. II-834–II-841 (2004)
Sharkas, M., Elenien, M.A.: Eigenfaces vs. fisherfaces vs. ICA for face recognition; a comparative study. In: 9th International Conference on Signal Processing, pp. 914–919 (2008)
Wolf, L., Hassner, T., Maoz, I.: Face recognition in unconstrained videos with matched background similarity. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 529–534 (2011)
Xie, C., Savvides, M., Vijaya Kumar, B.V.K.: Redundant class-dependence feature analysis based on correlation filters using FRGC2.0 data. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, p. 153 (2005)
Yan, Y., Wang, H., Suter, D.: Multi-subregion based correlation filter bank for robust face recognition. Pattern Recogn. 47(11), 3487–3501 (2014)
Yang, J., Zhang, D., Frangi, A.F., Yang, J.: Two-dimensional PCA: a new approach to appearance-based face representation and recognition. IEEE Trans. Pattern Anal. Mach. Intell. 26(1), 131–137 (2004)
Zeytunlu, A., Ahmad, M., Swamy, M.: Two-dimensional face recognition algorithms in the frequency domain. In: 25th IEEE Canadian Conference on Electrical Computer Engineering, pp. 1–4 (2012)
Zhang, D., Zhou, Z.H.: Two-directional two-dimensional PCA for efficient face representation and recognition. Neurocomputing 69(1–3), 224–231 (2005)
Acknowledgments
This work is supported by the National Science and Technology Council of Mexico (CONACyT), project #215546, scholarship #328839; and INAOE.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Alonso, V.E., Enríquez-Caldera, R., Sucar, L.E. (2017). A Two-Directional Two-Dimensional PCA Correlation Filter in the Phase only Spectrum for Face Recognition in Video. In: Nasrollahi, K., et al. Video Analytics. Face and Facial Expression Recognition and Audience Measurement. VAAM FFER 2016 2016. Lecture Notes in Computer Science(), vol 10165. Springer, Cham. https://doi.org/10.1007/978-3-319-56687-0_7
Download citation
DOI: https://doi.org/10.1007/978-3-319-56687-0_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-56686-3
Online ISBN: 978-3-319-56687-0
eBook Packages: Computer ScienceComputer Science (R0)