在近年來的學術界與產業界中，臉部辨識是一個受到眾人關注的話題。儘管現今已發展出許多演算法，但應用於現實環境中仍受到許多的挑戰。與全面 (holistic) 方法相比，局部 (local) 方法(如：local binary pattern (LBP) [4], [6]、local derivative pattern (LDP) [10] 與scale invariant feature transform (SIFT) [14] 等演算法)對於影像的細節描述地較為詳盡，故能得到較高的辨識率；但相對而言，局部方法的運算複雜度較高，會降低其應用的價值，如實現於行動裝置。此外，基於SIFT所發展出來的演算法，遇到光影有所變化的情況時，較無法維持良好的辨識率。因此，我們提出一個基於最大梯度特徵(Maxima of Gradient Magnitude, MGM [20])之局部二元模式與邊緣映射(LBP Edge-mapped)的描述子。這是一個具強健性且簡單、所需運算時間短的描述子。LBP Edge-mapped描述子藉由記錄最大梯度特徵周圍的亮度和邊緣資訊，進而得到一組二元碼。它不僅能完整地描述臉部的輪廓，還能同時擁有較低的運算複雜度。另外，由於描述子為二元模式，故我們可以使用一個簡單的方法來估測影像的相似程度、找到合適的配對。遇到光影不同的狀況時，實驗結果證明在FERET fc [22] 中，我們的方法不僅比SIFT高了約16.5%的辨識率，而且執行時間也節省了約9.06倍；在The Extended Yale Face Database B [32] 中，我們的方法明顯優於SIFT-based的方法，並比SIFT少了約70.9%的計算時間。面對臉部表情不同的情況時，FERET fb [22]的結果顯示我們的方法不僅可以維持令人接受的辨識率，還能比SIFT少花了7.50倍的運算時間。另外，於未受到任何條件限制的實際狀況中，我們使用UFI Database [30] 來評估方法的效能，並發現我們方法比local derivative pattern histogram sequences (LDPHS) 高了0.82%的辨識率。

Face recognition is one of popular topics in academic and industrial areas in recent years. Numerous approaches have been developed nowadays, but there are still several challenges in real-world circumstances. Present local methods such as local binary pattern (LBP) [4], [6], local derivative pattern (LDP) [10] and scale invariant feature transform (SIFT) [14] own better performance than holistic methods; however, high complexity results in some limitations for applications such as mobile devices. In addition, SIFT-based schemes are sensitive to illumination variation. Thus we propose a LBP Edge-mapped descriptor by using Maxima of Gradient Magnitude (MGM) [20] points. It is a robust, simple and fast descriptor. LBP Edge-mapped descriptor is a string of binary codes which record surrounding information of illumination and edges of MGM [20]. It can illustrate facial contours completely and have low computational complexity simultaneously. Due to binary codes, a simple matching method can be adopted for face recognition. Under variable lighting, experimental results show that our method has 16.5% higher recognition rate and spends 9.06 times less execution time than SIFT in FERET fc [22]. Besides, our method outperforms SIFT-based approaches and saves about 70.9% execution time compared with SIFT in the Extended Yale Face Database B [32]. In the variation of expression, our method maintains acceptable recognition rate and has 7.50 times less computational time than SIFT in FERET fb [22]. Furthermore, in uncontrolled conditions, our method owns 0.82% higher recognition rate than local derivative pattern histogram sequences (LDPHS) [10] in Unconstrained Facual Images (UFI) Database [30].

1 Introduction 1
1.1 Related Works 2
1.2 Motivation and Problem Description 3
1.3 Goal and Contribution 4
1.4 Thesis Organization 6
2 Maxima of Gradient Magnitude 7
2.1 Gradient and Edge Detection 9
2.2 Maxima of Gradient Magnitude (MGM) 11
3 Local Binary Pattern (LBP) Edge-mapped Descriptor for Face Recognition 14
3.1 Contrast Enhancement 15
3.2 LBP Edge-mapped Descriptor 20
3.3 Matching Method 23
4 Experimental Results 27
4.1 FERET Database 27
4.2 The Extended Yale Face Database B 35
4.3 Unconstrained Facial Images (UFI) Database 40
4.4 Helen Facial Feature Database 44
5 Conclusion and Future Work 47
Bibliography 49

[1] J. Lu, V. E. Liong, X. Zhou, and J. Zhou, “Learning Compact Binary Face Descriptor for Face Recognition,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 37, no. 10, pp. 2041-2056, Oct. 2015.
[2] M. Turk and A. Pentland, “Eigenfaces for Recognition,” Journal of Congnitive Neuroscience, vol. 3, no. 1, pp. 71-86, 1991.
[3] P. N. Belhumeur, J. P. Hespanha, and D. J. Kriegman,“Eigenfaces vs. Fisherfaces:
Recognition Using Class Specific Linear Projection” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 19, no. 7, pp. 711-720, Jul. 1997.
[4] T. Ojala, M. Pietikäinen, and D. Harwood, “A Comparative Study of Texture Measures with Classification Based on Feature Distributions,” Pattern Recognition, vol. 29, no. 1, pp. 51-59, 1996.
[5] T. Ojala, M. Pietikäinen, and T. Mäenpää, “Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns,” IEEE
Trans. Pattern Analysis and Machine Intelligence, vol. 24, no. 7, pp. 971-987, Jul. 2002.
[6] T. Ahonen, A. Hadid, and M. Pietikäinen, “Face Description with Local Binary Patterns: Application to Face Recognition,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 28, no. 12, pp. 2037-2041, Dec. 2006.
[7] C. Liu and H. Wechsler, “Gabor Feature Based Classification Using the Enhanced Fisher Linear Discriminant Model for Face Recognition,” IEEE Trans.
Image Process., vol. 11, no. 4, pp. 467-476, Apr. 2002.
[8] S. Zhao, Y. Gao, and B. Zhang, “SOBEL-LBP,” IEEE International Conference on Image Processing (ICIP), pp. 2144-2147, Oct. 2008.
[9] X. Tan and B. Triggs, “Enhanced Local Texture Feature Sets for Face Recognition Under Difficult Lighting Conditions,” IEEE Trans. Image Process., vol. 19, no. 6, pp. 1635-1650, Jun. 2010.
[10] B. Zhang, Y. Gao, S. Zhao, and J. Liu, “Local Derivative Pattern Versus Local Binary Pattern: Face Recognition with High-Order Local Pattern Descriptor,”
IEEE Trans. Image Process., vol. 19, no. 2, pp. 533-544, Feb. 2010.
[11] S. Xie, S. Shan, X. Chen, and J. Chen, “Fusing Local Patterns of Gabor Magnitude and Phase for Face Recognition,” IEEE Trans. Image Process., vol. 19, no. 5, pp. 1349-1361, May 2010.
[12] N. S. Vu, H. M. Dee, and A. Caplier, “Face Recognition Using The POEM Descriptor,” Pattern Recognition, pp. 2478-2488, 2012.
[13] S. U. Hussain, T. Napoléon, and F. Jurie, “Face Recognition Using Local Quantized Patterns,” Proc. Brit. Mach. Vis. Conf., pp. 1-12, 2012.
[14] D. G. Lowe, “Distinctive Image Features from Scale-Invariant Keypoints,” International Journal of Computer Vision, vol. 60, no. 2, pp. 91-110, Jan. 2004.
[15] J. Luo, Y. Ma, E. Takikawa, S. Lao, M. Kawade, and B. L. Lu, “Personspecific SIFT Features for Face Recognition,” IEEE International Conference
on Acoustics, Speech and Signal Processing (ICASSP), pp. 593-596, 2007.
[16] J. Krizaj, V. Struc, and N. Pavesić, “ Adaptation of SIFT Features for Robust Face Recognition,” International Conference Image Analysis and Recognition (ICIAR), pp. 394-404, 2010.
[17] P. Kamencay, M. Breznan, D. Jelsovka, and M. Zachariasova, “Improved Face Recognition Method based on Segmentation Algorithm Using SIFT-PCA,” Telecommunications and Signal Processing (TSP), pp. 758-762, 2012.
[18] Y. K. Shen and C. T. Chiu, “Local Binary Pattern Orientation Based Face Recognition,” IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1091-1095, Apr. 2015.
[19] S. Zhang, Q. Tian, K. Lu, Q. Hung, and W. Gao, “Edge-SIFT: Discriminative Binary Descriptor for Scalable Partial-Duplicate Mobile Search,” IEEE Trans. Image Process., vol. 22, no. 7, pp. 2899-2902, Jul. 2013.
[20] M. Faraji, J. Shanbehzadeh, K. Narollahi, and T. B. Moeslund, “Extremal Regions Detection Guided by Maxima of Gradient Magnitude,” IEEE Trans. Image Process., vol. 24, no. 12, pp. 5401-5415, Dec. 2015.
[21] P. J. Phillips, H. Wechsler, J. Huang, and P. J. Rauss, “The FERET Database and Evaluation Procedure for Face-recognition Algorithms,” Image and Vision Computing J, vol. 16, no. 5, pp. 295-306, 1998.
[22] P. J. Phillips, H. Moon, S. A. Rizvi, and P. J. Rauss, “The FERET Evaluation Methodology for Face-Recognition Algorithms,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 22, no. 10, pp. 1090-1104, Oct. 2000.
[23] J. Canny, “A Computational Approach to Edge Detection,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. PAMI-8, no. 6, pp. 679-698, Nov. 1986.
[24] Thomas B. Moeslund. (2012). Introduction to Video and Image Processing: Building Real Systems and Applications. London: Springer London.
[25] T. W. Ridler and S. Calvard, “Picture Thresholding Using an Iterative Selection Method,” IEEE Trans. Systems, Man, and Cybernetics, vol. SMC-8, no. 8, pp. 630-632, Aug. 1978.
[26] P. Viola and M. Jones, “Rapid Object Detection using a Boosted Cascade of Simple Features,” Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 511-518, 2001.
[27] Rafael C. Gonzalez and Richard E. Woods. (2008). Digital Image Processing: An Adapted Version (3rd ed.). Taiwan: Pearson Education Taiwan.
[28] K. Zuiderveld, “Contrast Limited Adaptive Histogram Equalization,” Graphic Gems IV, Academic Press, pp. 474-485, 1994.
[29] L. D. Huang, W. Zhao, J. Wang, and Z. B. Sun, “Combination of Contrast Limited Adaptive Histogram Equalisation and Discrete Wavelet Transform for Image Enhancement,” IET Image Processing, vol. 9, pp. 908-915, Sep. 2015.
[30] L. Lenc and P. Král, “Unconstrained Facial Images: Database for Face Recognition under Real-word Conditions,” Mexican International Conference on Artificial Intelligence (MICAI), pp. 349-361, Oct. 2015.
[31] A. S. Georghiades, P. N. Belhumeur, and D. J. Kriegman, “From Few to Many: Illumination Cone Models for Face Recognition under Variable Lighting and Pose,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol.
23, no. 6, pp. 643-660, Jun. 2001.
[32] K. C. Lee, J. Ho, and D. J. Kriegman, “Acquiring Linear Subspace for Face Recognition under Variable Lighting,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 27, no. 5, pp. 684-698, May 2005.
[33] L. Lenc and P. Král, “Automatically Detected Feature Positions for LBP Based Face Recognition,” Artificial Intelligence Applications and Innovations, pp. 246-255, 2014.
[34] V. Le, J. Brandt, Z. Lin, L. Bourdev, and T. S. Huang, “Interactive Facial Feature Localization,” 12th European Conference on Computer Vision, pp. 679-692, 2012.