臺灣博碩士論文加值系統

人臉辨識一直是學術界的熱門主題之一，其發展時間已久，其技術也越趨成熟，但在過去可能會受限於電腦硬體環境等因素等，以至需要在辨識正確率以及運算時間之間做取捨；如今隨著科技的進步以及硬體設備速度的提升，以往一些耗費大量時間、運算複雜度較高之方法，現今所需之運算時間已降低許多，使得這些方法漸趨可行。

本論文使用以機器學習為基礎的人臉偵測方法，結合膚色偵測、人眼特徵定位、鼻頭特徵定位、嘴部特徵定位以及機器學習的人臉辨識方法，準確定位出人臉，並擷取出人臉部的特徵值；接著使用類神經網路以及SVM等機器學習的方式，將所擷取出之臉部特徵值加以分類，以進行人臉辨識。

Human face detection and human face recognition are always popular topics in pattern recognition, they have develop for a long time, and its technique has become more and more robust. At the past, some technique could be restricted by hardware or other experimental settings, so they should made some kind of trade off between detection rate, recognition rate and computing time. Now days, with the development of technology and other equipment some time consuming methods become available.

We present a human face detection method which is base on haar-like features and integral image and a human face recognition method which divide human face into different feature area, then use machine learning to divide the feature groups and classify them by these feature information.

目錄
書名頁 i
論文口試委員審定書 ii
授權書 iii
中文摘要 iv
英文摘要 v
誌謝 vi
目錄 viii
圖目錄 xi
表目錄 x
第一章 緒論 1
1.1研究背景與動機 1
1.2研究目的 2
1.3論文大綱 3
第二章 文獻探討 4
2.1 簡介 4
2.2 人臉偵測 4
2.2.1 光線補償 5
2.2.2 彩色空間 5
2.2.3 膚色偵測 7
2.2.4 偵測眼部 8
2.2.5 眼位能量法 8
2.2.6 霍夫轉換 9
2.2.7 Adaboost 11
2.3 人臉辨識 12
2.3.1 特徵式 12
2.3.2 模板式 13
2.3.3 類神經網路 13
2.3.4 統計式 13
第三章 研究方法 14
3.1 研究架構 14
3.2 人臉偵測 15
3.2.1 積分影像（Integral Image） 15
3.2.2 矩形特徵（Rectangle Features） 17
3.2.3 Adaboost 19
3.2.4 Cascade of Strong Classifiers 19
3.3 人臉辨識 21
3.3.1 特徵區域擷取 21
3.3.2 眼部區域最佳化 22
3.3.3 嘴部區域最佳化 24
3.3.4 鼻部區域擷取 25
3.4 特徵點定位 26
3.4.1 內外眼角特徵點 26
3.4.2 嘴角特徵點 27
3.5 特徵值計算 28
3.6 Machine Learning 29
3.6.1 Neural Network 29
3.6.2 Support Vector Machines 31
第四章 研究結果 33
4.1 人臉資料庫 33
4.1.1 AT&T人臉資料庫 33
4.1.2 LFWcrop 人臉資料庫 34
4.1.3 Yale人臉資料庫 34
4.1.4 Georgia Tech 人臉資料庫 35
4.1.5 Caltech人臉資料庫 35
4.1.6 Indian Face Database 36
4.1.7 MIT CBCL face Database 36
4.2 實驗環境 37
4.3 實驗結果 37
4.3.1 單一人臉偵測 37
4.3.2 多重人臉偵測 41
4.3.3 人臉辨識 43
第五章 結論與未來展望 46
5.1 結論 46
5.2 未來展望 46






圖目錄
圖1 眼部偵測 8
圖2. 眼位能量法 9
圖5 原始影像與積分影像轉換 16
圖6 積分影像 17
圖7 各種矩形特徵 18
圖8 串聯強分類器 20
圖9 特徵區域 22
圖10 眼部邊緣偵測 23
圖11 與非膚色部分取交集 23
圖12 更新邊界後的特徵區域 23
圖13 邊緣偵測 24
圖14 嘴部更新後的左右邊界 25
圖15 鼻部區域 25
圖16 鼻部區域的邊緣偵測 26
圖17 內外眼角特徵點 27
圖18 嘴角特徵點 27
圖19 倒傳遞類神經網路 30
圖21 AT&T人臉資料庫 34
圖22 LFWcrop人臉資料庫 34
圖23 Yale人臉資料庫 35
圖24 Georgia tech人臉資料庫 35
圖25 caltech人臉資料庫 36
圖26 Indian face database 36
圖27 MIT CBCL face database 37
圖28 Caltech face DB 偵測結果 38
圖29 Georgia Tech face DB偵測結果 38
圖30 MIT CBCL face DB偵測結果 39
圖31 Indian face database偵測結果 39
圖32 影像過暗時無法偵測 40
圖33 人臉傾斜角度過大時無法成功偵測 40
圖34 自製圖庫偵測結果 43
圖35 左圖為特徵點定位成功 右圖為特徵點定位失敗 44

表目錄
表1 實驗環境 37
表2 各人臉資料庫偵測率 40
表3 Caltech face DB偵測率 41
表4 Georgia Tech face DB偵測率 41
表5 自製圖庫偵測率 43
表6 特徵點定位成功率 44
表7 各分類器辨識率 44
表8 各演算法辨識率 45

Reference

[1]G. Xin, and Z. Zhi-hua, "Image region selection and ensemble for face recognition," 2006.
[2]D. Anifantis, E. Dermatas, and G. Kokkinakis, "A neural network method for accurate face detection on arbitrary images." pp. 109-112 vol.1.
[3]H.C. Lee and C.S. Jong, “A Hybrid Neuro-Fuzzy Approach for AutomaticVehicle License Plate Recognition,” Applications and Science of Computational Intelligence, part of SPIE''s Aerospace/Defense Sensing and Controls, 1998.
[4]D. Enke, H.C. Lee, A.M. Ozbayoglu et al., “SimNet Neural Network: An Application to Speaker Identification,” University of Missouri-Rolla, Engineering Management Department, Rolla.
[5]P. Viola, and M. Jones, “Robust Real-Time Object Detection,” SECOND INTERNATIONAL WORKSHOP ON STATISTICAL AND COMPUTATIONAL THEORIES OF VISION – MODELING, LEARNING, COMPUTING, AND SAMPLING, 2001.
[6]S. K. D. Little, J. Black, S. Panchanathan, “A Methodology for Evaluating Robustness of Face Recognition Algorithm with Respect to Variations in Pose Angle and Illumination Angle,” IEEE International Conference on Acoustics Speech and Signal Processing, no. 6, pp. 89-92, 2005.
[7]C.-P. L. J.-T. Chien, “Nonsingular Discriminant Feature Extraction for Face Recognition,” IEEE International Conference on Acoustics Speech and Signal Processing, vol. 1.2, pp. 957-960, 2005.
[8]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, no. 5, pp. 696-706, May, 2002.
[9]C. P. Papageorgiou, M. Oren, and T. Poggio, “A General Framework for Object Detection,” Center for Biological and Computational Learning Artificial Intelligence Laboratory MIT Cambridge, MA 02139.
[10]R. Lienhart, and J. Maydt, “An Extended Set of Haar-like Features for Rapid Object Detection,” Intel Labs, Intel Corporation, Santa Clara, CA 95052, USA.
[11]S. B. H. A. Rowley, and T. Kanade, “Neural Network-Based Face Detection,” IEEE Translate on Pattern Analysis and Machine Intelligence, vol. 20, pp. 23-38, 1998.
[12]S. B. H. A. Rowley, and T. Kanade, “Rotation Invariant Neural Network-Based Face Detection,” Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition,, pp. 38-44, 1998.
[13]R. F. Edgar Osuna , Federico Girosi “Training Support Vector Machines: an Application to Face Detection ” Proc. Computer Vision and Pattern Recognition pp. 17-19, 1997.
[14]V. V. C. Cortes, “Support vector networks ” Machine Learning vol. 20, pp. 273-297, 1995.
[15]R. E. S. Yoav Freund “Experiments with a New Boosting Algorithm DRAFT ” Machine Learning: Proceedings of the Thirteenth International Conference, 1996.
[16]C. Yu-Ting, and C. Chu-Song, “Fast Human Detection Using a Novel Boosted Cascading Structure With Meta Stages,” Image Processing, IEEE Transactions on, vol. 17, no. 8, pp. 1452-1464, 2008.
[17]S. Baskan, M. M. Bulut, and V. Atalay, “Projection based method for segmentation of human face and its evaluation,” Pattern Recognition Letters, vol. 23, no. 14, pp. 1623-1629, 2002.
[18]R. S. J. Yang, U. Meier, and A. Waibel., “Real-time face and facial feature tracking and applications,” Proceedings of the International Conference on Auditory-Visual Speech Processing AVSP''98, pp. 79--84, 1998.
[19]P. V. C. Hough, “Method and means for recognizing complex patterns,” U. S. Patent 3, 069, 654,, 1962.
[20]N. H. Bergboer, E. O. Postma, and H. J. v. d. Herik, “Context-based object detection in still images,” Image and Vision Computing, vol. 24, no. 9, pp. 987-1000, 2006.
[21]R. C. Zhao W., P. J. Phillips, and A. Rosenfeld “Face Recognition: A Literature Survey ” ACM Computing Surveys vol. 35, 2003
[22]J. L. Stan Z. Li “Face Recognition Using the Nearest Feature Line Method,” Neural Networks, IEEE Transactions on, 1999.
[23]B. R. a. T. Poggio, “Face Recognition: Features versus Templates ” IEEE Transactions on Pattern Analysis and Machine Intellgence vol. 15, pp. 1042, 1993.
[24]S. W. Er M. J., J. Lu, and H. L. Toh “Face Recognition With Radial Basis Function (RBF) Neural Networks ” IEEE Transactions on Neural Networks vol. 13, 2002.
[25]M. E. Marshall B. Robinson, Jon Krueger, Doug Kochelek., “Face recognition using eigenfaces,” Computer Vision and Pattern Recognition,, 1991.
[26]G. I. Bicego M., and V. Murino “Face Recognition with Multilevel B-Splines and Support Vector Machines ” ACM WBMA’03 2003.
[27]A. B. Chris Messom “Fast and Efficient Rotated Haar-like Features using Rotated Integral Images ”.
[28]B. Moghaddam and A. Pentland, “Face Recognition using View-Based and Modular Eigenspaces,” Automatic Systems for the Identification and Inspection of Humans, 1994.
[29]P. H. B. Heisele, J. Wu, and T. Poggio, “Face recognition: component-based versus global approaches,” Computer Vision and Image Understanding, pp. 6-12, 2003.
[30]S. M. Mihir Jain1, Naresh Jotwani3, “Eye Detection and Face Recognition using Line Edge Maps,” IIIT, Hyderabad, 500032 DA-IICT, Gandhinagar, 382007.
[31]C.-J. Lin, H.-C. Chuang, and Y.-J. Xu, “Face detection in color images using efficient genetic algorithms,” Optical Engineering, vol. 45, no. 4, pp. 047201, 2006.
[32]X. M. Shan An, Rui Song and Yibin Li, “Face Detection and Recognition with SURF for Human-Robot Interaction,” IEEE, vol. School of Control Science and Engineering Shandong University 73 Jingshi Rd, Jinan, CHINA, 2009.
[33]D. Hall, “A system for object class detection,” INRIA Rh^one-Alpes, 655, ave de l''Europe, 38320 St. Ismier, France Daniela.Hall@inrialpes.fr.
[34]G. A. R. Jun Zheng, and Olac Fuentes, “Face Detection in Low-resolution Color Images,” Computer Science Department, University of Texas at El Paso, El Paso, Texas, 79968, U.S.A. jzheng@miners.utep.edu,garamirez@miners.utep.edu, ofuentes@utep.edu.
[35]A. Pal, “Multicues Face Detection in Complex Background for Frontal Faces,” International Machine Vision and Image Processing Conference, vol. Electronics and Communication Engineering, Indian Institute of Technology, Guwahati, Assam, India a.pal@iitg.ernet.in.
[36]A. Nigam, “A Novel Face Recognition Approach using Normalized Unmatched Points Measure,” DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING INDIAN INSTITUTE OF TECHNOLOGY KANPUR, 2009.
[37]S. K. M. Thomas , C. Kambhamettu, “Face Recognition using a color PCA framework ” Video/Image Modeling and Synthesis Lab, University of Delaware, Newark, DE 197112 Bell Laboratories, Lucent Technologies, 600 Mountain Avenue, Murray Hill, NJ 07974.