Abstract   Face  Recognition  (FR)  under  varying  pose  is  challe nging  and  exacting  pose  invariant  features  is  an  effective  approach  to  solve  this  problem.  In  this  paper,  we  propose a  novel  Truncated  Transform  Domain  Feature  Extractor  (TTDFE)  to improve the performance of the FR system. TTDFE involves a unique combination of Symlet-4 DWT, 2D-D CT, followed by  a novel truncation process. The truncation process  extracts higher amplitude coefficients from the Discrete Cosine Transform  (DCT ) matrix.  An  optimal  Truncation  Point  (TP)  is  estimat ed,  which  is  inspired  by  a  relationship  developed  between  the  image  dimensions  and  the  positions  of  DCT  amplitude   peaks.  TTDFE  is  used  for  efficient  feature  extraction  and  a  Binary   Particle  Swarm  Optimization  (BPSO)  based  feature  se lection  algorithm  is  used  to  search  the  feature  space  for  the  optimal  feature subset. Experimental results, obtained by a pplying the proposed algorithm on 5 benchmark  face  databases  with large  pose  variations,  namely  Facial  Recognition  Technolo gy  (FERET),  University  of  Manchester  Institute  of  Scien ce  and  Technology  ( UMIST),  Foundation  for  Education  of  Ignatius  (FEI),   Pointing’  04  Head  Pose  image  Database  (PHPD)  and  Indian   Face  Database  (IFD),  show  that  the  proposed  system  outperforms other  FR  systems.  A  significant  increase  in  the  Recognition Rate   (RR) and a substantial reduction in the number of featu res selected are observed.   

References

[1] Abate F., Michele N., Daniel R., and Gabriele S., 2D and 3D Face Recognition: A Survey, Pattern Recognition Letters , vol. 28, no. 14, pp. 1885-1906, 2007..

[2] Alex P., Baback M., and Thad S., View-based and Modular Eigenspaces for Face Recognition, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition , Seattle, pp. 84-91, 1994.

[3] Anthony P., Robert K., and Donald T., Comparing of Interpolation Methods for Image Resampling, IEEE Transactions on Medical Imaging , vol. 2, no. 1, pp. 31-39, 1983.

[4] Belhumeur N., Hespanha P., and Kriegman J., Eigenfaces vs. Fisherfaces: Recognition using Class Specific Linear Projection, IEEE Transactions on Pattern Analysis and Machine Intelligence , vol. 19, no. 7, pp. 711-720, 1997.

[5] Dai Q. and Yan H., Wavelets and Face Recognition, available at: http://cdn.intechopen.com/pdfs-wm/195.pdf, last visited 2007.

[6] Deepa M., Keerthi R., Meghana N., and Manikantan K., Face Recognition using Spectrum-based Feature Extraction, Applied Soft Computing Journal , vol. 12, no. 9, pp. 2913- 2923, 2012.

[7] Divya R., Anvesha R., Manikantan K., and Ramachandran S., Asteroid Shaped DCT Feature Extraction For Enhanced Face Recognition, in Proceedings of the CUBE International Information Technology Conference , Maharashtra, India, pp. 95-101, 2012.

[8] Eberhart C. and Kennedy J., A Discrete Binary Version of the Particle Swarm Algorithm, in Proceedings of IEEE International Conference on Systems, Man, and Cybernetics , Orlando, pp.4101-4108, 1997.

[9] Eberhart C. and Kennedy J., A New Optimizer using Particles Swarm Theory, in Proceedings of the 6 th International Symposium on Micro Machine and Human Science , Nagoya, pp. 39-43, 1995.

[10] Facial Recognition Technology Database., available at: http://www.itl.nist.gov/iad/humanid/ ferer/feretmaster.html, last visited 2014.

[11] FEIFaceDatabase., available at: http://fei.edu.br/ ~cet/facedatabase.html, last visited 2014.

[12] Gagan R., Hardik S., Manikantan K., and Ramachandran S., Circular Sector DCT based Feature Extraction for Enhanced Face Recognition using Histogram based Dynamic Gamma Intensity Correction, in Proceedings of CUBE International Information Technology Conference , Maharashtra, India, pp. 74-81, 2012.

[13] Gautham Y., Sankhadeep S., Manikantan K., and Ramachandran S., DWT Feature Extraction based Face Recognition using Intensity Mapped Unsharp Masking and Laplacian of Gaussian Filtering with Scalar Multiplier, in Proceedings of the 2 nd International Conference on Communication Computing and Security , pp. 475-484, 2012.

[14] Gonzalez, Rafael C., and Woods E., Digital Image Processing , Pierson Prentice Hall, 2007.

[15] Gourier N., Hall D., and Crowley L., Estimating Face Orientation from Robust Detection of Salient Facial Structures, in Proceedings of International Workshop on Visual Observation of Deictic Guestures , Cambridge, UK, pp. 1-9, 2004.

[16] Hafed M. and Levine D., Face Recognition using Discrete Cosine Transform, International Journal of Computer Vision , vol. 43, no. 3, pp. 167-188, 2001.

[17] Huang G., Ramesh M., Berg T., and Learned- Mill E., Labeled Faces in the Wild: A Database for Studying Face Recognition in Unconstrained Environments, available at: http://visw.cs.umass.edu/~vidit/IndianFaceDataas e/ , last visited 2014.

[18] Jian Y., David Z., Alejandro F., and Jing-yu Y., Two-Dimentional PCA: A New Approach to Appearance-based Face Representation and Recognition, IEEE Transactions on Pattern Analysis and Machine Intelligence , vol. 26, no. 1, pp. 131-137, 2004.

[19] Jihoon Y. and Vasant H., Feature Subset Selection using A Genetic Algorithm, IEEE Intelligent Systems and their Applications , vol. 13, no. 2, pp. 44-49, 1998.

[20] Kennedy J. and Eberhart C., Particle Swarm Optimization, in Proceedings of IEEE International Conference on Neural Networks , Perth, pp. 1942-1948, 1995.

[21] Kevin B., Kyong C., and Patrick F., A Survey of Approaches and Challenges in 3D and Multi- modal 3D+2D Face Recognition, Computer Vision and Image Understanding, vol. 101, no. 1, pp. 1-15, 2005.

[22] Marcos F., Josep R., Virginia E., and Jaun O., An Efficient Face Verification Method in a Transformed Domain, Pattern Recognition Letters , vol. 28, no. 7, pp. 854-858, 2007.

[23] Marian A., Salah A., and Islam Y., Efficient Web-based Facial Recognition System Employing 2DHOG, available at: http://arxiv.org/pdf/1202.2449.pdf, last visited 2012.

[24] Marian B., Javier M., and Terrence S., Face Recognition by Independent Component Analysis, IEEE Transactions on Neural Networks , vol. 13, no. 6, pp. 1450-1464, 2002. Face Recognition using Truncated Transform Domain Feature Extraction 219

[25] Mark N. and Alberto A., Feature Extraction and Image Processing , Elsevier, 2008.

[26] Marryam M., Muhammad S., Mudassar R., and Jamal S., Analysis of Face Recognition Under Varying Facial Expression: A Survey, the International Arab Journal of Information Technology , vol. 10, no. 4, pp. 378-388, 2013.

[27] Mathworks., available at: http://www.mathworks.in/products/matlab/, last visited 2014.

[28] Naveen M., Raghunandana R., Manikantan K., and Ramachandran S., Face Recognition using DWT Thresholding based Feature Extraction With Laplacian-Gradient Masking As a Pre- Processing Technique in Proceedings of the CUBE International Information Technology Conference, Maharashtra, India, pp. 82-89, 2012.

[29] Podilchuk C. and Zhang X., Face Recognition using DCT-based Feature Vectors, in Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing , Atlanta, pp. 2144-2147, 1996.

[30] Quan-xue G., Lei Z., and David Z., Face Recognition using FLDA with Single Training Image per Person, Applied Mathematics and Computation , vol. 205, no. 2, pp. 475-484, 2008.

[31] Ramadan M. and Abdel-Kader F., Face Recognition using Particle Swarm Optimization- based Selected Features, International Journal of Signal Processing, Image Processing and Pattern Recognition , vol. 2, no. 2, pp. 51-66, 2009.

[32] The Sheffield (previously UMIST- University of Manchester Institute of science and Technology) Face Database., available at: http://www.sheffield.ac.uk/eee/research/iel/resear ch/face, last visited 2014.

[33] Tolba S., El-baz H., and El-harby A., Face Recognition: A Literature Review, International Journal of Signal Processing, vol. 2, no. 2, pp. 399-458, 2006.

[34] Turk A. and Alex P., Face Recognition using Eigenfaces, in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition , Maui, pp. 586-591, 1991.

[35] Vidit J. and Amitabha M., The Indian Face Database: http:// vis-www.cs.umass.edu/ ~vidit/ IndianFaceDatabase/, last visited 2014.

[36] Xiaofei H., Shuicheng Y., Yuxiao H., Partha N., and Hong-Jiang Z., Face Recognition using Laplacianfaces, IEEE Transactions on Pattern Analysis and Machine Intelligence , vol. 27, no. 3, pp. 328-340, 2005.

[37] Zana Y., Cesar-Jr, Feris R., and Turk M., Local Approach for Face Verification in Polar Frequency Domain, Image and Vision Computing , vol. 24, no. 8, pp. 904-913, 2006. Rangan Kodandaram is pursuing BE degree (final year) in electronics and communication at MS Ramaiah Institute of Technology, India. His research interests include image processing, computer vision, business analytics and optimization. Currently, he is working on a project involving Computer Vision for Robotic Application. Shashank Mallikarjun is pursuing BE degree (final year) in electronics and communication engineering at MS Ramaiah Institute of Technology, India. His research interests are machine learning, artificial intelligence, computer vision, digital design, and image processing. Curre ntly, he is working on a project involving Computer Visio n for Robotic Applications. Manikantan Krishnamuthan holds a doctoral degree in pattern recognition and is currently an Associate Professor in the Department of electronics and communication engineering at M.S. Ramaiah Institute of Technology, India. His research interests include pattern recognition; image processing and FPGA based designs. Ramachandran Sivan is currently a Professor in the Department of Electronics and Communication Engineering at S. J. B. Institute of Technology, India. He obtained his MTech and PhD from IIT, Kanpur and Madras respectively. His research interests include developing algorithms, architectures and implementations on FPGA/ASICs for video processing, DSP applications, reconfigurable computing, and open loop control systems. He is the recipient of the Best Design Award at VLSI Design 2000, International Conference held at Calcutta, In dia and the Best Paper Award at WMSCI 2006, Orlando, Florida, USA. He has also written a book on Digital VLSI Systems Design, published by Springer Verlag, Netherlands (www.springer.com ).