在現實的應用中，監視攝影機在拍攝人臉時，由於距離過遠，造成辨識系統往往只能取得低解析度的影像。然而，低解析度的人臉會因資訊量的不足，造成辨識的準確度大幅度的降低。因此，為了克服此問題，我們提出結合可變區塊離散餘弦轉換。利用此方法，可以從低解析度人臉資訊中取得更多的人臉特徵。另外，分類器的選取上，我們採用高斯混合模型。但在計算最大概似機率的過程中，常常會含有部分的雜訊與不重要的資訊，導致辨識率的下降。針對此問題，我們提出可選高斯混和模型以解決此問題，並有效的提升辨識效果。最後，在實驗設計上，利用ORL資料庫與AR資料庫將大小次取樣為12x12像素實驗測試，我們證實提出的方法相較於在舊有方法更能在低解析度的情形下提高辨識率。此外，更利用AR資料庫中的部分遮蔽低解析度人臉加以實驗，相較於傳統方式，亦能獲得較佳的辨識效果。

The low resolution problem in face recognition, which often occurs in video surveillance applications, degrades the detection performance dramatically. To overcome the low resolution problem, in this thesis, we propose a novel face recognition system, which collects the observation vectors extracted from variable block discrete cosine transform (VB_DCT) and recognizes the identify by using selective likelihood Gaussian mixture modeling (SL_GMM). The VB_DCT successfully extends the observation vectors from small to global views of low resolution faces while the SL_GMM greatly helps to exclude insignificant local features during the recognition phase to improve the detection performance significantly. Experimental results, which were carried out on the ORL database and the AR database in size of 12×12 pixels after subsampling, show that the proposed method achieves better performance for low resolution face recognition, even under partial occlusion.

[1] W. Zhao, R. Chellappa, A. Rosenfeld, and P.J. Phillips, “Face Recognition: A Literature Survey,” ACM Computing Surveys,” vol. 35, no. 4, pp. 399-458, 2003.
[2] M. A. Turk and A. Pentland, “Eigenface for Recognition,” Journal of Cognitive Neuroscience, vol. 3, no. 1, pp. 71–86, 1991.
[3] P. N. Belhumeur, J. P. Hespanha, and D. J. Kriegman, “Eigenfaces vs. Fsherfaces: Recognition Using Class Specific Linear Projection,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 26, no. 4, pp. 711–720, 1997.
[4] B. Moghaddam and A. Pentland, “Probabilistic Visual Learning for Object Representation,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 19, no. 7, pp. 696–710, 1997.
[5] G. Dedeoglu, T. Kanade, and J. August, “High-zoom Video Hallucination by Exploiting Spatio-temporal Regularities,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol. 2, pp. 151–158, June 2004.
[6] S. Zhou, V. Krueger, and R. Chellappa, “Probabilistic Recognition of Human Face from Video,” Computer Vision, and Image Understanding, Special Issue on Face Recognition, vol. 91, pp. 214–245, 2003.
[7] S.W. Lee, J. Park, and S.W. Lee, “Low Resolution Face Recognition Based on Support Vector Data Description,” Pattern Recognition, vol. 39, no. 9, pp. 1809-1812, 2006.
[8] W.W.W. Zou and P.C. Yuen, “Very Low Resolution Face Recognition Problem,” in 2010 Fourth IEEE Conf. on Biometrics: Theory Applications and Systems (BTAS), 2010.
[9] S. Hayashi and O. Hasegawa, “Face Detection in Low-Resolution Images,” Lecture Notes in Computer Science, vol.3804, 2005.
[10] M. A. Turk and A. P. Pentland, "Face Recognition Using Eigenfaces," Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 586-591, 1991.
[11] P. N. Belhumeur, J. P. Hespanha, and D. J. Kriegman, "Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection," IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 19, pp. 711-720, 1997.
[12] G. Guo, S. Z. Li, and K. Chan, "Face Recognition by Support Vector Machines," Image and Vision Computing, vol. 19, pp. 631-638, 2001.
[13] C. Sanderson and K. K. Paliwal, “Fast Features for Face Authentication under Illumination Direction Changes,” Pattern Recognition Letters, vol. 24, no. 14, pp. 2409-2419, 2003.
[14] S. Zhao and R. R. Grigat, “Multiblock-Fusion Scheme for Face Recognition,” IEEE Conf. on Pattern Recognition, vol. 1, pp. 309-312, 2004.
[15] R. Gottumukkal and V. K. Asari, “An Improved Face Recognition Technique Based on Modular PCA Approach,” Pattern Recognition Letters, vol. 25, no. 4, pp. 429-436, 2004.
[16] Y. T. Chou, S. M. Huang, and J. F. Yang, “DWT and Sub-Pattern PCA for Face Recognition Based on Fuzzy Data Fusion,” IEEE Conf. on Intelligent Computation and Bio-medical Instrumentation, Wuhan, China, December 2011.
[17] S. M. Huang, Y. T. Chou, and J. F. Yang, “Multi-Resolution Local Probabilistic Approach for Low Resolution Face Recognition,” IEEE Conf. on Intelligent Computation and Bio-medical Instrumentation, Wuhan, China, December 2011.
[18] N. Ahmed, T. Natarajan, and K. R. Rao, “Discrete Cosine Transform,” IEEE Trans. on Computer, vol.23, no.1, pp.90-93, 1974.
[19] G. Günlü and H. S. Bilge, “Face Recognition with Discriminating 3D DCT Coefficients,” The Computer Journal, vol. 53, no.8, 2010.
[20] F. Cardinaux, C. Sanderson, and S. Bengio, “User Authentication via Adapted Statistical Models of Face Images,” IEEE Trans. on Signal Processing, vol. 54, no. 1, pp. 361 - 373, 2005.
[21] T. K. Moon, “The Expectation-maximization Algorithm,” IEEE Signal Processing Magazine, vol. 13, no. 6, pp. 47-60, November, 1996.
[22] AT&T Face Database [Online]. Available: http://www.cl.cam.ac.uk/research/dtg/attarchive/facedatabase.html, 2002.
[23] A. Martinez and R. Benavente, “The AR Face Database,” CVC Technical Report 24, 1998.
[24] A. Rama, F. Tarres, L. Goldmann, and T. Sikora, “More Robust Face Recognition by Considering Occlusion Information,” IEEE Conf. on Automatic Face and Gesture Recognition, 2008.
[25] S. Yan, H. Wang, J. Liu, X. Tang, and T. Huang, “Misalignment-Robust Face Recognition,” IEEE Trans. on Image Processing, vol. 19, no. 4, pp. 1087-1096, 2010.