Performance analysis of different matrix decomposition methods on face recognition

Applications using face biometric are ubiquitous in various domains. We propose an efficient method using Discrete Wavelet Transform (DWT), Extended Directional Binary codes (EDBC), three matrix decompositions and Singular Value Decomposition (SVD) for face recognition. The combined effect of Schur, Hessenberg and QR matrix decompositions are utilized with existing algorithm. The discrimination power between two different persons is justified using Average Overall Deviation (AOD) parameter. Fused EDBC and SVD features are considered for performance calculation. City-block and Euclidean Distance (ED) measure is used for matching. Performance is improved on YALE, GTAV and ORL face databases compared with existing methods.

[1]  Larry S. Davis,et al.  Label Consistent K-SVD: Learning a Discriminative Dictionary for Recognition , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  George Ghinea,et al.  Gradient-Orientation-Based PCA Subspace for Novel Face Recognition , 2014, IEEE Access.

[3]  Kenneth E. Barner,et al.  Locality Constrained Dictionary Learning for Nonlinear Dimensionality Reduction , 2013, IEEE Signal Processing Letters.

[4]  Radhey Shyam,et al.  Face recognition using augmented local binary pattern and Bray Curtis dissimilarity metric , 2015, 2015 2nd International Conference on Signal Processing and Integrated Networks (SPIN).

[5]  S. Meher,et al.  Performance improvement for face recognition using PCA and two-dimensional PCA , 2013, 2013 International Conference on Computer Communication and Informatics.

[6]  Haibo He,et al.  Learning Race from Face: A Survey , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Abdullah Bal,et al.  Component based scale and pose invariant face recognition , 2013, 2013 21st Signal Processing and Communications Applications Conference (SIU).

[8]  Jian-Jun Zhang,et al.  Self quotient image for face recognition , 2004, 2004 International Conference on Image Processing, 2004. ICIP '04..

[9]  S. Venkatramaphanikumar,et al.  Gabor based face recognition with dynamic time warping , 2013, 2013 Sixth International Conference on Contemporary Computing (IC3).

[10]  Enrique G. Ortiz,et al.  Computer Vision and Image Understanding , 2013 .

[11]  Xuelong Li,et al.  Data Uncertainty in Face Recognition , 2014, IEEE Transactions on Cybernetics.

[12]  John Soldera,et al.  Customized Orthogonal Locality Preserving Projections With Soft-Margin Maximization for Face Recognition , 2015, IEEE Transactions on Instrumentation and Measurement.

[13]  Antonio Rama,et al.  Face Recognition using a Fast Model Synthesis from a Profile and a Frontal View , 2007, 2007 IEEE International Conference on Image Processing.

[14]  Erhu Zhang,et al.  A single training sample face recognition algorithm based on sample extension , 2013, 2013 Sixth International Conference on Advanced Computational Intelligence (ICACI).

[15]  Guang-Ren Duan.  Right coprime factorizations using system upper Hessenberg forms-the multi-input system case , 2000, Proceedings of the 39th IEEE Conference on Decision and Control (Cat. No.00CH37187).

[16]  Kien A. Hua,et al.  Face recognition from a single registered image for conference socializing , 2015, Expert Syst. Appl..

[17]  Saeid Nahavandi,et al.  Recent Advances on Singlemodal and Multimodal Face Recognition: A Survey , 2014, IEEE Transactions on Human-Machine Systems.

[18]  E. Land,et al.  Lightness and retinex theory. , 1971, Journal of the Optical Society of America.

[19]  Katsumi Watanabe,et al.  Person Recognition Based on Memory of Back View , 2013, 2013 International Conference on Biometrics and Kansei Engineering.

[20]  Chandan Singh,et al.  Complementary feature sets for optimal face recognition , 2014, EURASIP J. Image Video Process..

[21]  George Bosilca,et al.  Parallel reduction to Hessenberg form with Algorithm-Based Fault Tolerance , 2013, 2013 SC - International Conference for High Performance Computing, Networking, Storage and Analysis (SC).

[22]  Terence Sim,et al.  When Fisher meets Fukunaga-Koontz: A New Look at Linear Discriminants , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[23]  Zia-ur Rahman,et al.  A multiscale retinex for bridging the gap between color images and the human observation of scenes , 1997, IEEE Trans. Image Process..

[24]  David Zhang,et al.  Introduction to the Special Section on Biometric Systems and Applications , 2014, IEEE Trans. Syst. Man Cybern. Syst..

[25]  Wonjun Hwang,et al.  SVD Face: Illumination-Invariant Face Representation , 2014, IEEE Signal Processing Letters.

[26]  Andy Harter,et al.  Parameterisation of a stochastic model for human face identification , 1994, Proceedings of 1994 IEEE Workshop on Applications of Computer Vision.

[27]  Yanwen Chong,et al.  Eigenface-Based Sparse Representation for Face Recognition , 2013, ICIC.

[28]  Vitomir Struc,et al.  Photometric Normalization Techniques for Illumination Invariance , 2011 .

[29]  Suthep Madarasmi,et al.  Face recognition improvement by converting expression faces to neutral faces , 2013, 2013 13th International Symposium on Communications and Information Technologies (ISCIT).

[30]  K Ramesha.  Performance Analysis of Face Recognition Based on Spatial and Transform Domain Techniques , 2013 .

[31]  Vitomir Struc,et al.  Gabor-Based Kernel Partial-Least-Squares Discrimination Features for Face Recognition , 2009, Informatica.

[32]  Zia-ur Rahman,et al.  Properties and performance of a center/surround retinex , 1997, IEEE Trans. Image Process..

[33]  Kiran B. Raja,et al.  A novel image fusion scheme for robust multiple face recognition with light-field camera , 2013, Proceedings of the 16th International Conference on Information Fusion.