IJE TRANSACTIONS A: Basics Vol. 32, No. 1 (January 2019) 78-84    Article in Press

PDF URL: http://www.ije.ir/Vol32/No1/A/10-2991.pdf  
downloaded Downloaded: 69   viewed Viewed: 551

M. Shavandi and I. E. P. Afrakoti
( Received: November 16, 2018 – Accepted in Revised Form: January 03, 2019 )

Abstract    Despite recent advances in face recognition systems, they suffer from serious problems because of the extensive types of changes in human face (changes like light, glasses, head tilt, different emotional modes). Each one of these factors can significantly reduce the face recognition accuracy. Several methods have been proposed by researchers to overcome these problems. Nonetheless, in recent years, using thermal images has gain more attention among the introduced solutions as an effective and unique solution. This article studies the performance of sparse processing techniques when facing with challenges of face recognition problem in thermal images. Also, the potential of the sparse classifier algorithm to receive information directly from input images without using any feature extraction algorithms was studied. The obtained results indicated that the sparse processing techniques outperform the Eigenface and KNN algorithms in terms of addressing the challenges of thermal images. In this work, USTC NVIN and CBSR NIR face datasets were used for simulation purposes. These datasets include the images with different emotional states (sad, happy, etc.) captured in different light conditions; also the images are captured both with and without wearing glasses. Simulation results have shown that sparse classifier can be an effective algorithm for the face recognition problem in thermal images.


Keywords    Face Recognition, Sparse Representations Classification, Thermal Images, Norm l^0



سیستم‌های شناسایی چهره علی¬رغم پیشرفت‌های بسیاری که داشته‌اند به دلیل طیف وسیع تغییرات چهره انسان (تغییراتی مانند: نور، عینک، چرخش سر، حالت‌های عاطفی مختلف) هنوز هم با مشکلاتی مواجه هستند. راه حل‌های مختلفی از سوی محققان جهت غلبه بر این مشکلات مطرح شده است، اما در سال‌های اخیر از بین این راه حل‌ها استفاده از تصاویر حرارتی به عنوان راه حلی موثر و خاص مورد توجه قرار گرفته است. در این مقاله به بررسی عملکرد روش‌های پردازش تنک در مواجه با چالش‌های شناسایی تصاویر حرارتی چهره پرداخته شده است. همچنین توانمندی الگوریتم طبقه‌بند تنک در دریافت اطلاعات به صورت مستقیم از تصاویر ورودی بدون استفاده از هیچ گونه الگوریتم استخراج ویژگی مورد ارزیابی قرار گرفته است. نتایج بدست آمده از شبیه‌سازی حاکی از برتری روش‌های پردازش تنک نسبت به الگوریتم‌های Eigenface، KNN در مقابله با چالش‌های تصاویر حرارتی می‌باشد. در این کار از دو مجموعه داده‌ی USTC.NVIN وCBSR NIR Face Dataset جهت شبیه‌سازی استفاده شده است. تصاویر موجود در این پایگاه‌های داده شامل تصاویر با حالت چهره مختلف (غم،شادی و...)، که در شرایط نوری متفاوتی تهیه شده‌اند و همچنین تصاویر باعینک و بی‌عینک می‌باشد. نتایج شبیه‌سازی توانایی الگوریتم‌های تنک را در مواجهه با مساله شناسایی چهره در تصاویر حرارتی تایید می‌کند.


1. Ghiass, R.S., Arandjelovic, O., Bendada, H. and Maldague, X., "Infrared face recognition: A literature review", in Neural Networks (IJCNN), The 2013 International Joint Conference on, IEEE. (2013), 1-10.
2. Mostafa, E., Hammoud, R., Ali, A., Farag, A.J.C.V. and Understanding, I., "Face recognition in low resolution thermal images",   Computer Vision and Image Understanding Vol. 117, No. 12, (2013), 1689-1694.
3. Friedrich, G. and Yeshurun, Y., "Seeing people in the dark: Face recognition in infrared images", in International Workshop on Biologically Motivated Computer Vision, Springer, Berlin, Heidelberg, (2002), 348-359. 
4. Kakkirala, K.R., Chalamala, S.R. and Jami, S., "Thermal infrared face recognition: A review",  In Computer Modelling & Simulation (UKSim), 2017 UKSim-AMSS 19th International Conference on,. IEEE, (2017), 55-60. 
5. Kong, S.G., Heo, J., Abidi, B.R., Paik, J., Abidi, M.A.J.C.V. and Understanding, I., "Recent advances in visual and infrared face recognition—a review", Computer Vision and Image Understanding , Vol. 97, No. 1, (2005), 103-135.
6. Cutler, R.G., "Face recognition using infrared images and eigenfaces",  University of Maryland, (1996). 
7. Majumder, G. and Bhowmik, M.K., "Gabor-fast ica feature extraction for thermal face recognition using linear kernel support vector machine", in Computational Intelligence and Networks (CINE), 2015 International Conference on, IEEE. (2015), 21-25.
8. Zhang, X., Peng, M. and Chen, T., "Face recognition from near-infrared images with convolutional neural network", in Wireless Communications & Signal Processing (WCSP), 2016 8th International Conference on, IEEE, (2016), 1-5.
9. Wu, Z., Peng, M. and Chen, T., "Thermal face recognition using convolutional neural network", in Optoelectronics and Image Processing (ICOIP), 2016 International Conference on, IEEE.  (2016), 6-9.
10. Zhao, S., Grigat, R.-R.J.M.L. and Recognition, D.M.i.P., "An automatic face recognition system in the near infrared spectrum", In International Workshop on Machine Learning and Data Mining in Pattern Recognition, Springer, Berlin, Heidelberg, (2005), 633-633.
11. Cho, S.-Y., Wang, L. and Ong, W.J., "Thermal imprint feature analysis for face recognition", in Industrial Electronics, 2009. ISIE 2009. IEEE International Symposium on, IEEE. (2009), 1875-1880.
12. Seal, A., Bhattacharjee, D., Nasipuri, M. and Basu, D.K., "Minutiae based thermal face recognition using blood perfusion data", in Image Information Processing (ICIIP), 2011 International Conference on, IEEE. (2011), 1-4.
13. Awedat, K., Essa, A. and Asari, V., "Sparse representation classification based linear integration of l-norm and l 2-norm for robust face recognition", (2017).
14. Reihanian, S., Arbabi, E. and Maham, B., "Random sparse representation for thermal to visible face recognition", in Computers and Communications (ISCC), 2017 IEEE Symposium on, IEEE.  (2017), 1380-1385.
15. Wright, J., Yang, A.Y., Ganesh, A., Sastry, S.S., Ma, Y..a. and intelligence, m., "Robust face recognition via sparse representation",  IEEE Transactions on Pattern Analysis and Machine Intelligence,  Vol. 31, No. 2, (2009), 210-227. 
16. Mohimani, H., Babaie-Zadeh, M. and Christian J., "A fast approach for overcomplete sparse decomposition based on smoothed l^0 norm", IEEE Transactions on Signal Processing, Vol. 57, No. 1, (2009), 289-301.
17. Tropp, Joel A., and Anna C. Gilbert. "Signal recovery from random measurements via orthogonal matching pursuit." IEEE Transactions on Information Theory, Vol. 53, No. 12 (2007): 4655-4666.
18. Pati, Y.C., Rezaiifar, R. and Krishnaprasad, P.S., "Orthogonal matching pursuit: Recursive function approximation with applications to wavelet decomposition", in Signals, Systems and Computers. 1993 Conference Record of The Twenty-Seventh Asilomar Conference on, IEEE. (1993), 40-44.
19. Nvie database. A Natural Visible and Infrared facial Expression Database; Available from: http://nvie.ustc.edu.cn.
20. Cbsr nir face dataset. OTCBVS Benchmark Dataset Collection; Available from: http://vcipl-okstate.org/pbvs/bench/index.html.
21. Martinez, B., Binefa, X. and Pantic, M., "Facial component detection in thermal imagery", Computer Vision and Pattern Recognition Workshops (CVPRW), 2010 IEEE Computer Society Conference on, IEEE. (2010), 48-54.
22. Lin, Chun-Fu, and Sheng-Fuu Lin. "Accuracy enhanced thermal face recognition." Infrared Physics & Technology, Vol. 61 (2013), 200-207.
23. Farokhi, Sajad, Jan Flusser, and Usman Ullah Sheikh. "Near infrared face recognition: A literature survey." Computer Science Review, Vol. 21 (2016), 1-17.
24. Howland, Peg, Jianlin Wang, and Haesun Park. "Solving the small sample size problem in face recognition using generalized discriminant analysis." Pattern Recognition, Vol. 39, No. 2 (2006): 277-287.
25. Shobeirinejad, A. and Gao, Y., "Gender classification using interlaced derivative patterns", in Pattern Recognition (ICPR), 2010 20th International Conference on, IEEE. (2010), 1509-1512.

Download PDF 

International Journal of Engineering
E-mail: office@ije.ir
Web Site: http://www.ije.ir