生物特徵具有唯一性與獨特性因此可用來做身分識別的用途。人臉影像取得容易且屬於非接觸式擷取，同時取像設備僅需要一般相機即可，建置成本相對於其他技術較低。人臉識別可應用的範圍相當廣泛，使其成為生物特徵辨識主流技術之一。由於人臉影像容易受到外在因素變化影響，為提高辨識率本論文乃加強前處理與相似度計算方式。影像前處理先進行亮度正規化(Illumination Normalization) ，同時利用索貝爾梯度(Sobel Gradient)做邊的強化，再以多尺度局部二元圖型(Multi-scale Block Local Binary Pattern)為基礎進行特徵擷取，並利用LBP-TOP將不同尺度之特徵混合起來，取得人臉中各種尺度的特徵資訊。辨識方式結合Distance Transform與Earth Mover’s Distance(EMD)直方圖(histogram)的相似度計算方式，提出新的辨識演算法，讓辨識時同時考慮到特徵值的空間分佈與直方圖數量分佈情況，並依照配對的特徵點數制定出自適性門檻值(Adaptive Threshold)。經由實驗證實，辨識率比現有的方法有較好的效果。

Biometrics can be used as human identification due to uniqueness and specificity. Face image which is non-contact acquisition can be captured easily and compared to other techniques it can be established by a quite cheap webcam. Face recognition can be applied in many aspects and it becomes one of major biometric identification technologies. Because face image is vulnerable to environment, to improve the recognition rate, we strengthen the pre-processing and similarity calculation in this dissertation. For the former, first the brightness is improved by Illumination Normalization and the edges are enhanced by Sobel Gradient. Based on the LBP-TOP and Local Binary Pattern, the features are then extracted in different scales. A new recognition algorithm is proposed based on the Distance Transform similarity calculation method combined with the Earth Mover's Distance (EMD). It then considers both the spatial distribution and histogram distribution. Based on the number of feature points matched, an adaptive threshold is set for each user. Compared to other existing methods, experiment results show that the proposed method has the better recognition rate.

[1] 科技產業資訊室, http://cdnet.stpi.narl.org.tw/techroom/market/eetelecomm_mobile/2013/eetelecomm_mobile_13_042.htm
[2] R. L. Hsu, M. Abdel-Mottaleb, and A. K. Jain, “Face Detection in Color Images”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 24, pp. 696-706, 2002.
[3] P. Viola and M. Jones, “Rapid Object Detection Using a Boosted Cascade of Simple Features”, Computer Vision and Patterns Recognition, IEEE Computer Society Conference, vol. 1, pp. I-511-518, 2001.
[4] Gonzalez Woods, “Digital Image Processing”, 普林斯頓國際, 民國九十七年十二月, 初版
[5] 鐘國亮, “影像處理與電腦視覺”, 東華書局, 民國九十五年三 月, 三版
[6] B.A. Draper, K. Baek, M.S. Bartlett, and J.R. Beveridge, “Recognizing Faces with PCA and ICA”, Computer Vision and Image Understanding, vol. 91, no. 1, pp. 115-137, 2003
[7] M. A. Turk and A. P. Pentland, “Face Recognition Using Eigenfaces”, IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 586-591, 1991.
[8] T. Ahonen, A. Hadid, and M. Pietikainen, ”Face Recognition with Local Binary Patterns”, In Proc. ECCV, 2004.
[9] Giovani G_omez, “Local Smoothness In Terms of Variance the Adaptive Gaussian Filter”, ITESM Campus Morelos. Apdo. postal 99-C, pp. 815-824, 2000.
[10] M. I. Ribeiro, “Gaussian Probability Density Functions: Properties and Error Characterization”, Technical Report, IST, 2004
[11] Xiaoyang Tan, Bill Triggs, “Enhanced local texture feature sets for face recognition under difficult lighting conditions”, IEEE Transactions on Image Processing, VOL. 19, NO. 6, JUNE 2010.
[12] T. Chen,W. Yin, X. Zhou, D. Comaniciu, and T. Huang, “Total variation models for variable lighting face recognition”, IEEE Tpami, 28(9):1519–1524, 2006.
[13] N. Vu and A. Caplier, “Enhanced Patterns of Oriented Edge Magnitudes for Face Recognition and Image Matching”, IEEE Transactions on Image Processing, VOL. 21, NO. 3, 2012
[14] S. Liao, X. Zhu, Z. Lei, L. Zhang, and S. Z. Li, “Learning Multi-scale Block Local Binary Patterns for Face Recognition”, ICB2007, LNCS 4642, pp. 828-837, 2007.
[15] 施佑駿, “Face Recognition System Based on Local Regions and Multi-resolution Analysis”, 國立台灣科技大學資訊工程系, 2010.
[16] G. Zhao and M. Pietikainen, “Dynamic Texture Recognition Using Local Binary Patterns with an Application to Facial Expressions”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 29, No. 6, pp.915-928, 2007.
[17] G. Borgefors, “Distance Transformations in Digital Images”, Computer Vision, Graphics and Image Processing, vol. 35, pp. 344-371, 1986.
[18] Yossi Rubner, Carlo Tomasi and Leonidas J. Guibas, “The Earth Mover’s Distance as a Metric for Image Retrieval”, International Journal of Computer Vision 40(2), 99–121, 2000
[19] Gamma Correction Technical Brief Copyright by Codonics Inc.
http://www.codonics.com
[20] C. Liu and H. Wechsler, “A Gabor Feature Classifier for Face Recognition”, IEEE International Conference on Computer Vision, vol. 2, pp. 270-275, 2001.
[21] X. Tan and B. Triggs, “Fusing Gabor and LBP Feature Sets for Kernel-Based Face Recognition,” in Analysis and Modelling of Faces and Gestures, vol. 4778, pp. 235 – 249, 2007.
[22] Ojala, M. Pietikainen, and T. Maenpaa, “Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 24, no. 7, pp.971-987, 2002.
[23] T. Ahonen, A. Hadid, and M. Pietikainen, “Face Description with Local Binary Patterns: Application to Face Recognition”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 28, no. 12, pp. 2037-2041, 2006.
[24] Z. Xinjun, S. Zhipeng and S. Jinguang, “Face recognition Algorithm Based On SIFT and LBP”, HHME2011, 2011
[25] S. Liao and A. C. S. Chung, “Texture Classification By Using Advanced Local Binary Patterns and Spatial Distribution of Dominant Patterns”, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2007.
[26] “Distance Transform”
http://en.wikipedia.org/wiki/Distance_transform
[27] “FERET Database”
http://www.itl.nist.gov/iad/humanid/feret/
[28] “YaleDatabase” http://cvc.yale.edu/projects/yalefaces/yalefaces.html
[29] “Faces94Database”
http://cswww.essex.ac.uk/mv/allfaces/faces94.html
[30] Maria De Marsico, Michele Nappi, Daniel Riccio, and Harry Wechsler, “Robust Face Recognition for Uncontrolled Pose and Illumination Changes”, IEEE TRANSACTIONS ON SYSTEMS, MAN, AND CYBERNETICS: SYSTEMS, VOL. 43, NO. 1, JANUARY 2013
[31] Shih-Ming Huang and Jar-Ferr Yang “Linear Discriminant Regression Classification for Face Recognition”, IEEE SIGNAL PROCESSING LETTERS, VOL. 20, NO. 1, JANUARY 2013
[32] G. Prabhu Teja, S. Ravi “Face Recognition using Subspaces Techniques”, Recent Trends In Information Technology (ICRTIT), 2012, P.103-P.107, 19-21, April 2012
[33] Javier Ruiz-del-Solar and Pablo Navarrete “Eigenspace-Based Face Recognition: A Comparative Study of Different Approaches”, IEEE TRANSACTIONS ON SYSTEMS, MAN, AND CYBERNETICS—PART C: APPLICATIONS AND REVIEWS, VOL. 35, NO. 3, AUGUST 2005
[34] Wenchao Zhang, Shiguang Shan, Wen Gao, Xilin Chen, Hongming Zhang “Local Gabor Binary Pattern Histogram Sequence (LGBPHS): A Novel Non-Statistical Model for Face Representation and Recognition”, Tenth IEEE International Conference on Computer Vision, 2005. ICCV 2005. 786 - 791 Vol. 1, Oct, 2005
[35] Meng Yang, Lei Zhang, Simon Chi-Keung Shiu and David Zhang “Robust Kernel Representation With Statistical Local Features for Face Recognition”, IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, VOL. 24, NO. 6, JUNE 2013
[36] C.H. Hoi and M.R. Lyu, “Robust face recognition using minimax probability machine”, 7th International Conference on Automatic Face and Gesture Recognition, 2006
[37] S. Damavandinejadmonfared, W. H. Al-arashi, and S. A. Suandi, “Pose Invariant Face Recognition for Video Surveillance System Using Kernel Principle Component Analysis”, Engineering, pp. 3-7,MAY 2012.
[38] Guojun LIN and Mei XIE, “A Face Recognition Algorithm Using Local Binary Patterns and Locality Preserving Projections”, Journal of Information & Computational Science 9: 16 (2012) 5059–5067, DEC 2012
[39] GL Marcialis and F. Roli, “Fusion of lda and pca for face recognition,” in 8th Congress of Italian Association for Artificial Intelligence, Siena, 2002.