臺灣博碩士論文加值系統

本論文中提出一套高效率的人臉識別系統，可以應用到門禁管制、保全監控、互動服務等系統中。此識別系統主要包含人臉偵測以及人臉辨識兩個子系統。
人臉偵測系統中，利用膚色找到人臉的搜尋區域後，再以橢圓樣板演算法，找出可能為人臉的影像，最後以主分量分析（Principal Component Analysis，PCA）確認偵測到的影像是否為人臉影像。
人臉辨識系統中，使用離散小波轉換（Discrete Wavelet Transform，DWT）以及線性鑑別式分析（Linear Discriminate Analysis，LDA）得到具有鑑別性的特徵參數，在測試時以最接近特徵線（Nearest Feature Line，NFL）做為分類法則，建立起一套強健而準確的辨識系統。
實驗結果顯示，在人臉偵測中，偵測正確率為96.2%，所需時間約28ms；在人臉辨識部分，辨識率能達到94.56%，在Pentium M 1.5G中辨識一位成員所需的時間僅需8.37ms。

In this thesis, an efficient face identification system is proposed. The system can be applied to a security monitoring, doorway intercom and interactivity service, etc. The identification system mainly consists of two sub-systems: one is face detection and another is face recognition.
The face detection sub-system detects face search region using skin color information. We detect the possible face images using an ellipse template algorithm, and finally the human face using principal component Analysis (PCA).
For the face recognition sub-system, we can extract the low-dimensional discriminative feature parameter for human faces using the discrete wavelet transform (DWT) and Linear Discriminant Analysis (LDA). Finally, we employ the nearest feature line (NFL) to determine the most likely person. We can construct a robust and high-accuracy recognition system.
The experimental results in face detection part show that the successful rate is 98.4%. For the face recognition part, the recognition rate for a single image reaches 94%. Finally, the computation time of the entire face recognition system is 0.26 seconds on the average, using a Pentium M 1.5G personal computer.

中文摘要 I
Abstract II
誌謝 III
目錄 IV
圖目錄 VIII
表目錄 XI
第 1 章 緒論 1
1.1 研究動機 1
1.2 研究目的 2
1.3 系統概觀 3
1.4 論文架構 5
第 2 章 相關研究回顧 6
2.1 人臉偵測 6
2.2 人臉辨識 9
第 3 章 人臉偵測與驗證 13
3.1 人臉偵測驗證流程 13
3.2 膚色檢驗程序 14
3.2.1 影像白色平衡 14
3.2.2 膚色範圍檢測 17
3.2.3 雜訊移除程序 19
3.2.4 連接元區域標定程序 21
3.2.5 場景動態偵測 23
3.3 橢圓臉部搜尋程序 24
3.3.1 平滑濾波 25
3.3.2 邊緣偵測 26
3.3.3 橢圓樣板搜尋 27
3.4 人臉驗證 30
3.4.1 主分量分析 31
3.4.2 基本運作原理 32
3.4.3 人臉樣本訓練 34
3.4.4 人臉驗證程序 37
第 4 章 人臉辨識 40
4.1 人臉辨識流程 40
4.2 人臉辨識-影像前處理 42
4.2.1 人臉正規化 42
4.2.2 臉部亮度調整 42
4.3 離散小波轉換 43
4.4 線性鑑別式分析 47
4.4.1 簡介 47
4.4.2 基本運作原理 48
4.4.3 線性鑑別分析的缺點 53
4.5 辨識分類法則 56
4.5.1 歐式距離 56
4.5.2 最接近特徵線 57
第 5 章 實驗結果與討論 60
5.1 實驗環境與設備 60
5.2 人臉偵測實驗結果 60
5.2.1 膚色偵測 60
5.2.2 人臉偵測 62
5.2.3 偵測正確率分析 66
5.3 人臉驗證實驗結果 68
5.3.1 主成份分析之效能分析 68
5.3.2 人臉驗證之誤差門閥值 71
5.3.3 驗證正確率分析 72
5.4 人臉辨識實驗結果 74
5.4.1 人臉資料庫 74
5.4.2 特徵參數之比較 76
5.4.3 線性鑑別式分析之影響 79
5.4.4 分類法則之比較 82
5.4.5 辨識正確率分析 83
第 6 章 結論與未來展望 85
6.1 結論 85
6.2 未來研究方向 86
參考文獻 87
附錄一、ORL人臉影像資料庫 90
附錄二、Yale人臉影像資料庫 91
附錄三、SILAB人臉影像資料庫 92

[1] P. Belhumeur, J. Hespanha and D. Kriegman, “Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection,” IEEE Trans. , pp.711-720, July 1997.
[2] M. Turk and A. Pentland, “Eigenfaces for Recognition,” Jour. of Cognitive Neuroscience, vol. 3, pp.71-86, 1991.
[3] Garcia, C.; Tziritas, G. “Face Detection Using Quantized Skin Color Regions Merging and Wavelet Packet Analysis,” IEEE Tran. Multimedia, vol. 1, pp.264-277, September 1999.
[4] CCIR. 1982. CCIR Recommendation 601-1. Encoding parameters of digital television for studios., 1982-1986.
[5] C. Liu, and H. Wechsler, “Gabor Feature Based Classification Using the Enhanced Fisher Linear Discriminant Model for Face Recognition,” Proc. of IEEE Trans. on Image Processing, vol.11, pp.467- 476, 2002.
[6] W. S. Lee, H. J. Lee, and J. H. Chung, “Wavelet-Based FLD for Face Recognition,” Proc. of IEEE Midwest Symp. on Circuits and Systems, pp.734-737, August 2000.
[7] D. L. Swets and J. J. Weng, “Using Discriminant Eigenfeatures for Image Retrieval,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 18, pp.831-836, August 1996.
[8] L. G. Shapiro, G. C. Stockman, “Computer Vision,” pp.65-68,
Prentice-Hall, NJ, 2001.
[9] S.Z. Li , J. Lu, ”Face Recognition Using the Nearest Feature Line
Method,” IEEE Trans. Neural Networks , vol.10, pp.439-443,
March 1999.
[10] Linda G. Shapiro , G. C. Stockman “Computer Vision,” pp.65-68, Prentice-Hall, NJ, 2001.
[11] Aleix M. Martinez, and Avinash C. Kak, “PCA versus LDA,” IEEE
Transactions on Pattern Analysis and Machine Intelligence, vol. 23,
pp.228-233, February 2001
[12] K. Etemad, and R. Chellappa, “Discriminant Analysis for Recognition of Human Face Images,” vol.14, pp.1724-1733, 1997.
[13] M. Nagao, M. Yamamoto, K. Suzuki, A. Ohuchi, “MTS Approach to Facial Image Recognition,”. Proc. IEEE Conf. On Systems, Man, and Cybernetics. vol.4 , pp.937-942, 1999.
[14] S. Birchfield, “An Elliptical Head Tracker,” Conf. Record of the Asilomar Conf. on Signals, Systems & Computers, vol.2, pp.1710-1714, November 1997.
[15] S. Birchfield, “Elliptical Head Tracking Using Intensity Gradients and Color Histograms,” Proc. of the IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, pp.232-237, June 1998.
[16] M.-H. Yang, D. Kriegman, and N. Ahuja, “Detecting faces in images: A survey,” IEEE Trans. on Pattern Anal. Mach. Intelligence, vol.24, pp.34-58, 2002.
[17] M. F. Augusteijn and T. L. Skujca, “Identification of Human Faces through Texture-Based Feature Recognition and Neural Network technology,” Proc. IEEE Conf. Neural Networks, pp.392-398, 1993.
[18] R. Chellappa, C. Wilson, and S. Sirohey, “Human and machine recognition of faces: a Survey,” in Proceedings of IEEE, vol.83, May 1995.
[19] G. Yang and T. S. Huang, “Human Face Detection in Complex Background,” Pattern Recognition, vol.27, pp.53-63, 1994.
[20] H. P. Graf, T. Chen, E. Petajan, and E. Cosatto, “Locating Faces and Facial Parts,” Proc. First Int’l Workshop Automatic Face and Gesture Recognition, pp.41-46, 1995.
[21] T. K. Leung, M. C. Burl, and P. Perona, “Finding Faces in Cluttered Scenes Using Random Labeled Graph Matching,” Proc. Fifth IEEE Int’l Conf. Computer Vision, pp.637-644, 1995.
[22] Y. Dai and Y. Nakano, “Face-Texture Model Based on SGLD and Its Application in Face Detection in a Color Scene,” Pattern Recognition, vol. 29, pp.1007-1017, 1996.
[23] K.-K. Sung and T. Poggio, “Example-based learning for view-based human face detection,” IEEE Trans. on Pattern Analysis and Machine Intelligence, pp.39-51, 1998.
[24] K. Sobottka and I. Pitas, “Face localization and feature extraction base on shape and color information,” Proc. of IEEE Int’l Conf. on Image Processing, pp.483-486, 1996.
[25] H. Wu, Q. Chen, and M. Yachida, “Face Detection from Color Images Using a Fuzzy Pattern Matching Method,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol.21, pp.557-563, June 1999.
[26] J. Miao, B. Yin, K. Wang, L. Shen, and X. Chen, “A hierarchical Multiscale and Multiangle System for Human Face Detectoin in a Complex Background Using Gravity-Center Template,” Pattern Recognition ,vol.32, pp.1237-1248, 1999.
[27] I. Craw, H. Ellis, and J. Lishman, “Automatic Extraction of Face Features, ”Pattern Recognition Letters, vol.5, pp.183-187, 1987.
[28] L. Sirovich and M. Kirby, “Low-dimensional procedure for the characterization of human faces,” J. Opt. Soc. Amer.4, pp.519-524, 1987.
[29] R. Brunelli and T. Poggio, “Face recognition: Features versus templates” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 15, pp.1042-1052, 1993.
[30] T. Kanade, “Picture Processing by Computer Complex and Recognition of Human Faces,” PhD thesis, Kyoto University, 1973.
[31] Ara V. Nefian and Monson H. Hayes III, “Hidden Markov Models for Face Recognition,” Center for Signal and Image Processing School of Electrical and Computer Engineering Georgia Institute of Technology, Atlanta.
[32] Hua Yu, Jie Yang, “A Direct lda algorithm for high dimensional data with application to face recognition”, Pattern Recognition, pp.2067-2070, vol.34, 2001.
[33] Lawrence, S., Giles, C.L., Ah Chung Tsoi, Computer Vision and Pattern Recognition, 1996. Proceedings CVPR '96, 1996 IEEE Computer Society Conference, pp.217 -222, Jun 1996.
[34] Cover, T. M. and Thomas, J. A., Elements of Information Theory, John Willey and Sons, 1991.
[35] M.Hasegawa , Y.Nasu , “A Method of Face Images by Using Multiplex Resolution Image “ , IEICE Tech , Report PRU 89-26 , pp.57-60, 1989.