SPECIAL ISSUE: Facial Image Processing and Analysis; Edited by M. Grgic, S. Shan, R. Lukac, H. Wechsler and M. S. BartlettNo Access

FACIAL BIOMETRICS USING NONTENSOR PRODUCT WAVELET AND 2D DISCRIMINANT TECHNIQUES

DAN ZHANG

Department of Computer Science, Hong Kong Baptist University, Hong Kong

Search for more papers by this author

XINGE YOU

Department of Electronics and Information Engineering, Huazhong University of Science and Technology, Wuhan, China, 430074, China

Author for correspondence.

Search for more papers by this author

PATRICK WANG

College of Computer and Information Science, Northeastern University, Boston, MA, USA

Search for more papers by this author

SVETLANA N. YANUSHKEVICH

Department of Electrical and Computer Engineering, University of Calgary, Alberta, Canada

Search for more papers by this author

, and

YUAN YAN TANG

Department of Computer Science, Hong Kong Baptist University, Hong Kong

Search for more papers by this author

https://doi.org/10.1142/S0218001409007260Cited by:39 (Source: Crossref)

Abstract

A new facial biometric scheme is proposed in this paper. Three steps are included. First, a new nontensor product bivariate wavelet is utilized to get different facial frequency components. Then a modified 2D linear discriminant technique (M2DLD) is applied on these frequency components to enhance the discrimination of the facial features. Finally, support vector machine (SVM) is adopted for classification. Compared with the traditional tensor product wavelet, the new nontensor product wavelet can detect more singular facial features in the high-frequency components. Earlier studies show that the high-frequency components are sensitive to facial expression variations and minor occlusions, while the low-frequency component is sensitive to illumination changes. Therefore, there are two advantages of using the new nontensor product wavelet compared with the traditional tensor product one. First, the low-frequency component is more robust to the expression variations and minor occlusions, which indicates that it is more efficient in facial feature representation. Second, the corresponding high-frequency components are more robust to the illumination changes, subsequently it is more powerful for classification as well. The application of the M2DLD on these wavelet frequency components enhances the discrimination of the facial features while reducing the feature vectors dimension a lot. The experimental results on the AR database and the PIE database verified the efficiency of the proposed method.

Keywords:

References

R. Bolle et al. , Guide to Biometrics ( Springer , 2004 ) . Crossref, Google Scholar
R. Brunelli and T. Poggio, IEEE Trans. PAMI 15(10), 1042 (1993). Crossref, Web of Science, Google Scholar
Q. Chenet al., SIAM J. Matrix Anal. Appl. 25(2), 517 (2003), DOI: 10.1137/S0895479802412735. Crossref, Web of Science, Google Scholar
Q. Chen, C. A. Micchelli and Y. Xu, Linear. Algeb. Appl. 402, 111 (2005), DOI: 10.1016/j.laa.2004.12.028. Crossref, Web of Science, Google Scholar
C. Chen and P. Wang , Handbook of Pattern Recognition and Computer Vision ( World Scientific , 2005 ) . Link, Google Scholar
J. T. Chien and C. C. Wu, IEEE Trans. Patt. Anal. Mach. Intell. 24(12), 1644 (2002). Crossref, Web of Science, Google Scholar
A. Cohen and I. Daubechies, Rev. Mat. Iberoamericana 9, 51 (1993). Crossref, Google Scholar
T. Cooke, IEEE Trans. PAMI 24(2), 268 (2002). Crossref, Google Scholar
I. Daubechies , Ten Lectures on Wavelets , Society for Industrial and Applied Mathemathics ( Philadelphia , 1992 ) . Crossref, Google Scholar
H. K. Ekenel and B. Sanker, Imag. Vis. Comput. 23, 469 (2005). Crossref, Web of Science, Google Scholar
P. Ekman and E. L. Rosenberg , What the Face Reveals: Basic and Applied Studues of Spontaneouse Expression Using the Facial Action Coding System ( Oxford University Press , 1997 ) . Google Scholar
K. Etemad and R. Chellappa, J. Opt. Soc. Am. A 14(8), 1724 (1997), DOI: 10.1364/JOSAA.14.001724. Crossref, Google Scholar
G. C. Feng, P. C. Yuen and D. Q. Dai, J. Electron. Imag. 9(2), 226 (2000), DOI: 10.1117/1.482742. Crossref, Web of Science, Google Scholar
H.-H. Gao, H.-H. Yang and X.-Y. Wang, Kernel PCA based network inrusion feature extraction and dectection using svm, Proc. ICNC3611, Lecture Notes in Computer Science (2005) pp. 89–94. Google Scholar
C. Garcia, G. Zikos and G. Tziritas, A wavelet-based framework for face recognition, Proc. Workshop on Advances in Facial Image Analysis and Recognition Technology, 5th European Conference on Computer Vision (ECCV'98) (1998) pp. 84–92. Google Scholar
W. He and M. J. Lai, IEEE Trans. Imag. Process. 9(8), 949 (2000). Crossref, Web of Science, Google Scholar
A. Jain , R. Bolle and S. Pankanti , Biometrics: Personal Identification in a Networked Society ( Kluwer , 1999 ) . Crossref, Google Scholar
R. Q. Jia and C. A. Micchelli, Computing 48, 61 (1992), DOI: 10.1007/BF02241706. Crossref, Web of Science, Google Scholar
M. Kirby and L. Sirovich, IEEE Trans. Patt. Anal. Mach. Intell. 12(1), 103 (1990), DOI: 10.1109/34.41390. Crossref, Web of Science, Google Scholar
C. Kotropoulos, A. Tefas and L. Pitas, IEEE Trans. PAMI 23(7), 735 (2001). Web of Science, Google Scholar
J. Kovacevic and M. Vetterli, IEEE Trans. Inform. Th. 38, 533 (1992), DOI: 10.1109/18.119722. Crossref, Web of Science, Google Scholar
G. Lanckrietet al., Neural Computation (2002). Google Scholar
S.-W. Leeet al., Int. J. Patt. Recogn. Artif. Intell. 22(3), 389 (2008), DOI: 10.1142/S0218001408006272. Link, Web of Science, Google Scholar
Y. Luoet al., Simulation of biometric information: the new generation of biometric systems, Proc. Int. Workshop Modeling and Simulation in Biometric Technology (2004) pp. 87–98. Google Scholar
Y. Ma, M. Schuckers and B. Cukic, Guidelines for appropriate use of simulated data for bio-authentication research, Proc. 4th IEEE Workshop Automatic Identification Advanced Technologies (2005) pp. 251–256. Google Scholar
T. Moriyamaet al., Meticulously detailed eye model and its application to analysis of facial image, Proc. IEEE Int. Conf. Syst. Man Cybern.24 (2004) pp. 629–634. Google Scholar
K. Muller, B. Scholkopf and A. Smola, Advances in Kernel Methods — Support Vector Learning, eds. B. Scholkopf, C. Burges and A. Smola (MIT Press, 1999) pp. 327–352. Google Scholar
C. Nastar, The image shape spectrum for image retrieval, Technical Report, INRIA, No. 3206 (June 1997) . Google Scholar
C. Nastar, B. Moghaddam and A. Pentland, Comput. Vis. Imag. Underst. 65(2), 179 (1997), DOI: 10.1006/cviu.1996.0583. Crossref, Web of Science, Google Scholar
V. D. M. Nhat and S. Lee, Line-based PCA and LDA approaches for face recognition, Proc. ICNC3611, Lecture Notes in Computer Science (2005) pp. 101–104. Google Scholar
N. M. Orlans, D. J. Buettner and J. Marques, A survey of synthetic biometrics: capabilities and benefits, Proc. Int. Conf. Artificial Intelligence (2004) pp. 499–505. Google Scholar
M. Pantic and L. J. M. Rothkrantz, IEEE Trans. PAMI 22(12), 1424 (2000). Crossref, Google Scholar
N. Ratha, J. Connell and R. Bolle, IBM Syst. J. 40(3), 614 (2001). Crossref, Web of Science, Google Scholar
S. D. Riemenschneider, R. Q. Jia and D. X. Zhou, SIAM J. Matrix Anal. Appl. 21, 1 (1999). Web of Science, Google Scholar
A. Ross , K. Nandakumar and A. Jain , Int. Series on Biometrics ( Springer , 2006 ) . Google Scholar
M. Safari, M. T. Harandi and B. N. Araabi, A SVM-based method for face recognition using a wavelet PCA representation of faces, Proc. IEEE Int. Conf. Image Processing (2004) pp. 24–27. Google Scholar
C. Sanchez-Avila and R. Sanchez-Reillo, IEEE Aerosp. Electron. Syst. Mag. 24(3), 3 (2002). Google Scholar
V. Shmerkoet al., Biometric technologies, Proc. Int. Conf. Biometrics: fraud Prevention, Enchanced Service (1997) pp. 270–286. Google Scholar
L. Sirovich and M. Kirby, J. Opt. Soc. Am. 4, 519 (1987), DOI: 10.1364/JOSAA.4.000519. Crossref, Web of Science, Google Scholar
M. Turk and A. Pentland, J. Cogn. Neurosci. 3(1), 71 (1991), DOI: 10.1162/jocn.1991.3.1.71. Crossref, Web of Science, Google Scholar
M. Vetterli, Signal Proc. 10(3), 219 (1986), DOI: 10.1016/0165-1684(86)90101-5. Crossref, Web of Science, Google Scholar
J. Wayman, A. Jain, D. Maltoni and D. Maio, Biometric systems technology, design and performance evaluation (Springer, 2005) . Google Scholar
W. S. Yambor, Analysis of PCA-based and Fisher discriminant-based image recognition, Technical Report, Department of Computer Science, Colorado State University (2000) . Google Scholar
J. Yanget al., IEEE Trans. PAMI 26(1), 131 (2004). Crossref, Web of Science, Google Scholar
S. N. Yanushkevich et al. , Biometric Inverse Problems ( Taylor & Francis/CRC Press , Boca Raton, FL , 2005 ) . Crossref, Google Scholar
S. N. Yanushkevichet al., Simulation of biometric information: the new generation of biometric systems, Proc. Int. Workshop Modeling and Simulation in Biometric Technology (2004) pp. 87–98. Google Scholar
X. You, Q. Chen, D. Zhang, P. Wang and Y. Y. Tang, Face recognition based on new non-separable wavelet, Technical Report, Deparment of Computer Science, Hong Kong Baptist University (January 2007) . Google Scholar
X. You, L. Du, Q. Chen and Y. Cheung, Significant difference watermarking using new non-tensor wavelet filter banks, Technical Report, Department of Electronics and Information, Huazhong University of Science and Technology, 2007 . Google Scholar
X. Youet al., Face representation by using non-tensor product wavelets, 18th Int. Conf. Patt. Recogn. (2006) pp. 503–506. Google Scholar
W. Zhao and R. Chelappa , Face Processing: Advanced Modeling and Methods ( Elsevier , 2006 ) . Google Scholar
B. L. Zhang, H. H. Zhang and S. S. Ge, IEEE Trans. Neural Networks 15(1), 166 (2004), DOI: 10.1109/TNN.2003.820673. Crossref, Web of Science, Google Scholar
Z. B. Zhang, S. L. Ma and D. Y. Wu, Adv. Neural Networks 828 (2005). Google Scholar