Fast face recognition approach using a graphical processing unit “GPU”

In this manuscript, we present an implementation of a correlation method for face recognition application on GPU. Our correlator is based on the famous “4f” setup and the use of a Phase Only Filter (POF). Traditionally, the correlation method is implemented using optical components for real-time application. Unfortunately, optical implementation is complex and has exorbitant price. To cope with these drawbacks and in order to benefit from the accuracy of the correlation method, we propose in this work to implement the correlation using GPU. To this end, we will take an interest in the mathematical aspect of the correlation method to identify the processing to be implemented on GPU. Simulations results about the implementation of the face recognition application on GPU showed the efficiency of our proposed design. Moreover, comparison between GPU and CPU in terms of execution time have been made and shows that, to identify one face among 4, GPU Nvidia Geforce 8400 GS is 3 times faster than the Intel Core 2 CPU 2.00 GHZ (using Matlab).

[1]  A. W. M. van den Enden,et al.  Discrete Time Signal Processing , 1989 .

[2]  J L Horner,et al.  Metrics for assessing pattern-recognition performance. , 1992, Applied optics.

[3]  J L de Bougrenet de la Tocnaye,et al.  Optical implementation of segmented composite filtering. , 1999, Applied optics.

[4]  Kenneth Moreland,et al.  The FFT on a GPU , 2003, HWWS '03.

[5]  Ayman Alfalou,et al.  Understanding Correlation Techniques for Face Recognition: From Basics to Applications , 2010 .

[6]  C. Rader.  Discrete Fourier transforms when the number of data samples is prime , 1968 .

[7]  Ningfang Liao,et al.  Study of ARFTIS reconstruction model on GPU , 2009, 2009 ISECS International Colloquium on Computing, Communication, Control, and Management.

[8]  Steven G. Johnson,et al.  The Design and Implementation of FFTW3 , 2005, Proceedings of the IEEE.

[9]  J. Tukey,et al.  An algorithm for the machine calculation of complex Fourier series , 1965 .

[10]  B.J. Henz,et al.  Coprocessor Computing with FPGA and GPU , 2008, 2008 DoD HPCMP Users Group Conference.

[11]  Ayman Alfalou,et al.  A new simultaneous compression and encryption method for images suitable to recognize form by optical correlation , 2009, Security + Defence.

[12]  Martin Vetterli,et al.  Fast Fourier transforms: a tutorial review and a state of the art , 1990 .

[13]  Habib Hamam,et al.  Mobil phone camera Recognition Sign Language using a segmented multidecision filter adapted to the Parallel virtual machine (PVM) , 2008 .