Non-linear Feature Fusion Based on Polynomial Correlation Filter for Face Recognition

Face recognition is an active research area due to its wide range of practical applications. Efficient and discriminative facial feature is a crucial issue for face recognition. Most existing methods use one type of features but we show that robust face recognition requires different kinds of feature information to be taken into account. Traditional feature fusion methods are based on the linear combination. In this study, we propose a novel and effective fusion method (called NF-PCF), which uses polynomial correlation filter (PCF) to non-linearly fuse different types of features for robust face recognition. Experimental results on two popular face databases, including Yale and PIE, show the promising results obtained by the proposed method.

[1]  Jiri Matas,et al.  On Combining Classifiers , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Matti Pietikäinen,et al.  Face Description with Local Binary Patterns: Application to Face Recognition , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Marcin Michalak,et al.  Support Vector Machines in Biomedical and Biometrical Applications , 2013 .

[4]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[5]  David G. Lowe,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004, International Journal of Computer Vision.

[6]  Marios Savvides,et al.  Correlation Pattern Recognition for Face Recognition , 2006, Proceedings of the IEEE.

[7]  Oscar Déniz-Suárez,et al.  Face recognition using Histograms of Oriented Gradients , 2011, Pattern Recognit. Lett..

[8]  Chengjun Liu,et al.  Fusion of color, local spatial and global frequency information for face recognition , 2010, Pattern Recognit..

[9]  David J. Kriegman,et al.  Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection , 1996, ECCV.

[10]  Azriel Rosenfeld,et al.  Face recognition: A literature survey , 2003, CSUR.

[11]  Allen Y. Yang,et al.  Robust Face Recognition via Sparse Representation , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  Urbano Nunes,et al.  Trainable classifier-fusion schemes: An application to pedestrian detection , 2009, 2009 12th International IEEE Conference on Intelligent Transportation Systems.

[13]  Yuxiao Hu,et al.  Face recognition using Laplacianfaces , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  D. Casasent,et al.  Minimum average correlation energy filters. , 1987, Applied optics.

[15]  M. Turk,et al.  Eigenfaces for Recognition , 1991, Journal of Cognitive Neuroscience.

[16]  Thomas S. Huang,et al.  Image processing , 1971 .

[17]  Chengjun Liu,et al.  A shape- and texture-based enhanced Fisher classifier for face recognition , 2001, IEEE Trans. Image Process..

[18]  Mita Nasipuri,et al.  Face Recognition by Fusing Local and Global Discriminant Features , 2011 .

[19]  Yu-Jin Zhang,et al.  1D correlation filter based class-dependence feature analysis for face recognition , 2008, Pattern Recognit..

[20]  David J. Kriegman,et al.  From Few to Many: Illumination Cone Models for Face Recognition under Variable Lighting and Pose , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[21]  P. Réfrégier.  Filter design for optical pattern recognition: multicriteria optimization approach. , 1990, Optics letters.

[22]  Arun Ross,et al.  Score normalization in multimodal biometric systems , 2005, Pattern Recognit..

[23]  B. V. Vijaya Kumar,et al.  Minimum-variance synthetic discriminant functions , 1986 .