Abstract
The fractional Fourier transform (FrFT) features have been known to be effective for face recognition. However, only a few approaches utilize phase feature and they usually perform worse than those using magnitude feature. To investigate the potential of FrFT phase and its fusion between different orders for face recognition, in this paper, we first propose weighted multi-order band fusion of generalized phase spectrum (WMFP) of 2D-FrFT. Compared with the conventional appearance-based face recognition method, the proposed method does not need to perform image-to-vector conversion and can well preserve the discriminative information of the original image. Different from the existing Fourier-based recognition approaches such as Fourier-LDA and local region histogram of 2D-FrFT magnitude and phase (LFMP), the proposed approach merges multiple orders’ generalized phase spectrum of 2D-FrFT and gives different weights to different orders simultaneously. Experimental results on two benchmark face databases demonstrate the effectiveness of the proposed method and indicate that our method is better than Fourier-PCA and LFMP, as well as other popular face recognition methods such as Gabor-based linear discriminant analysis (GLDA) and local Gabor binary patterns (LGBP).
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
REFERENCES
Jain, A., Ross, A., Prabhakar, S.: An introduction to biometric recognition. IEEE Trans. Circ. Syst. Video Technol. 14(1), 4–20 (2004)
Jing, X.Y., Tang, Y.Y., Zhang, D.: A Fourier-LDA approach for image recognition. Pattern Recogn. 38(3), 453–457 (2005)
Sao, A.K., Yegnanarayana, B.: On the use of phase of the Fourier transform for face recognition under variations in illumination. Sig. Image Video Process. 4(3), 353–358 (2010)
Gao, L., Qi, L., Chen, E.Q., Mu, X.M., Guan, L.: Recognizing human emotional state based on the phase information of the two dimensional fractional Fourier transform. In: 11th Pacific Rim Conference on Multimedia, pp. 694–794 (2010)
Tao, R., Qi, L., Wang, Y.: The theory and Applications of Fractional Fourier Transform. Tsinghua University Press, Beijing (2004)
Jing, X.Y., Wong, H.S., Zhang, D.: Face recognition based on discriminant fractional Fourier feature extraction. Pattern Recogn. Lett. 27(13), 1465–1471 (2006)
Pei, S.C., Ding, J.J.: Relations between fractional operations and time-frequency distributions and their applications. IEEE Trans. Sig. Process. 49(8), 1638–1655 (2001)
Choi, S.: Combined features for face recognition. Electron. Lett. 52(1), 0013–5194 (2016)
Belhumeur, P.N., Hespanha, J.P., Kriegman, D.J.: Eigenfaces vs. Fisherfaces: recognition using class specific linear projection. IEEE Trans. Pattern Anal. Mach. Intell. 19(7), 711–720 (1997)
Wright, J., Yang, A.Y., Ganesh, A., Sastry, S.S., Ma, Y.: Robust face recognition via sparse representation. IEEE Trans. Pattern Anal. Mach. Intell. 31(2), 210–227 (2009)
Luan, X., Fang, B., Liu, L.H., Yang, W.B., Qian, J.: Extracting sparse error of robust PCA for face recognition in the presence of varying illumination and occlusion. Pattern Recogn. 47(2), 495–508 (2014)
Liu, C., Wechsler, H.: Gabor feature based classification using the enhanced Fisher linear discriminant model for face recognition. IEEE Trans. Image Process. 11, 467–476 (2002)
Zhang, W., Shan, S., Gao, W., et al.: Local Gabor Binary Pattern Histogram Sequence (LGBPHS): a novel non-statistical model for face representation and recognition. In: International Conference on Computer Vision, pp. 786–791 (2005)
Kong, M., Qi, L., Zheng, N., et al.: Application of the 2D-FrFT combined with fuzzy fusion classification algorithm in human emotional state recognition. In: TMEE, pp. 1094–1097 (2011)
Wang, Y.X., Qi, L., Guo, X., Gao, L.: Face recognition based on histogram of the 2DFrFT magnitude and phase. In: Information Science, Electronics and Electrical Engineering (ISEEE), vol. 3, pp. 1421–1425 (2014). doi:10.1109/6946154
Acknowledgments
This work was supported in partly by the National Natural Science Foundation of China under Grant No. 61331201 and No. 61201251.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Wang, X., Qi, L., Tie, Y., Chen, E. (2017). Face Recognition Based on Weighted Multi-order Feature Fusion of 2D-FrFT. In: Yang, X., Zhai, G. (eds) Digital TV and Wireless Multimedia Communication. IFTC 2016. Communications in Computer and Information Science, vol 685. Springer, Singapore. https://doi.org/10.1007/978-981-10-4211-9_14
Download citation
DOI: https://doi.org/10.1007/978-981-10-4211-9_14
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-4210-2
Online ISBN: 978-981-10-4211-9
eBook Packages: Computer ScienceComputer Science (R0)