臺灣博碩士論文加值系統

隨著科學技術不斷的進步與發展，快速與準確儼然已成為生物特徵辨識的基本特點。生物特徵辨識中物件比對的方法有許多種，利用形狀偵測及邊緣偵測都是在物件比對中常見的方法。而人臉辨識是一個典型的圖像分析、圖像分解及分類的綜合運用。由於人臉是最為複雜、分析種類最為龐大的人類生物特徵，目前對這一問題的初步研究與解決，是在物件比對上找到穩定的參考點做為比對。
在此課題下，本文研究探討人臉辨識之方法，提出改善辨識系統反應時間。藉由網路攝影機所拍攝到之影像，以及使用者使用網路環境，開啟網頁進行使用者臉部偵測。記錄使用者正面影像，提供辨識系統進一步進行人臉辨識。也就是本研究論文欲探討及解決的問題。
本篇論文以二元二維主成份分析法(Binary Two Dimensional Principal Component Analysis,B2DPCA) 方法進行了人臉辨識實驗，並設計在兩種不同網域環境及六種不同情境下進行實驗測試。實驗結果顯示本研究提出的方法有效加快人臉辨識率及系統反應時間，並實踐在人臉辨識課程線上點名系統，有效提升教師對於上課學生出席率的掌控。

As scientific technology has continuously improved and developed, rapidity and accuracy has become the basic and essential features of biometric identification. There are many different kinds of methods to deal with objects comparison in biometric identification. For instance, shape detection and edge detection are both commonly used in biometric identification. However, face recognition is a typically integrated application of image analysis, image decomposition and classification. While the face is the most complex biological feature which the widest varieties of analysis are needed, the current solution to this is mostly to find stable reference points for objects comparison.
Therefore, the purpose of this study is to explore the methods of face recognition and improve its response time of the recognition system. The images taken by webcams and the Internet environment of the users which have been enable the user to do the face detection via Internet websites. Furthermore, those records of the user’s frontal face have been provided further face recognition for identification system. The above is that the research question wants to be discussed and solved.
The experiment of face recognition in this paper has been conducted through Binary Two Dimensional Principal Component Analysis (B2DPCA). Moreover, the experiment has been done with two different network environment and six different situations. The results have shown that the methods in our study effectively accelerate the rate of face recognition and assist the teachers in having better control of the attendance rate while the face recognition has been applied in online course attendance system.

摘要 ............................................................................................................ i
Abstract ....................................................................................................... ii
表目錄 .......................................................................................................... vi
圖目錄 .......................................................................................................... vii
第一章 緒論 ....................................................................................................... 1
1.1 研究動機與背景 ........................................................................................ 1
1.2 相關研究 .................................................................................................... 2
1.3 論文架構 .................................................................................................... 4
第二章 文獻蒐集與探討 ........................................................................................ 5
2.1 影像處理相關知識 .................................................................................... 5
2.1.1. 灰階影像 ........................................................................................ 5
2.1.2. 二值化 ............................................................................................ 6
2.1.3. Canny邊緣偵測 ............................................................................ 7
2.1.4. 色彩空間 ...................................................................................... 10
2.1.5. 侵蝕與膨脹 .................................................................................. 11
2.1.6. 連通演算法 .................................................................................. 13
2.2 人臉偵測 .................................................................................................. 14
2.2.1. 圖片光線補償 ................................................................................... 15
2.2.2. 人臉膚色模型 ................................................................................... 15
2.2.3. 人類臉部區域偵測 ........................................................................... 17
2.2.4. 人類臉部區域篩選 ........................................................................... 17
2.2.5. Haar 人類臉區域檢測法 .................................................................. 18
2.2.6. 人臉Haar特徵偵測 ......................................................................... 19
2.2.7. 人類Haar特徵快速算法 ................................................................. 21
2.3 人類臉部辨識 .......................................................................................... 23
2.3.1. 主成分分析法 ................................................................................... 24
2.3.2. 二維主成分分析法 ........................................................................... 25
2.3.3. 2DPAC人類臉部特徵提取 .............................................................. 26
2.3.4. 2DPAC分類器 .................................................................................. 27
2.3.5. 基於2DPCA的圖像重新組構 ........................................................ 28
第三章 人臉辨識演算法 ...................................................................................... 29
3.1 人類臉部區域偵測 .................................................................................. 30
3.1.1. 人臉膚色模型 ................................................................................... 30
3.1.2. 人類臉部區域偵測 ........................................................................... 32
3.1.3. 人類臉部區域篩選 ........................................................................... 32
3.2 人類臉部辨識 .......................................................................................... 33
3.2.1. 人臉區域正規化 ............................................................................... 33
3.2.2. 色彩空間轉換 ................................................................................... 33
3.2.3. YCbCr色彩空間 ............................................................................... 34
3.2.4. HSV 色彩空間 .................................................................................. 35
3.2.5. 訓練人臉資料庫 ............................................................................... 36
3.2.6. B2DPCA 二元二維主成份分析 ...................................................... 36
3.2.7. 分類 ................................................................................................... 38
3.2.8. 歐式距離 ........................................................................................... 39
3.3 課程線上點名系統介紹 .......................................................................... 40
3.3.1. 課程線上點名網頁系統架構 ........................................................... 41
3.3.2. 課程線上點名網頁系統流程圖 ....................................................... 41
第四章 實驗結果 .................................................................................................. 44
4.1 實驗環境與設備 ...................................................................................... 44
4.1.1. 實驗環境 ........................................................................................... 46
4.1.2. 人臉資料庫 ....................................................................................... 47
4.2 人臉辨識實驗結果與分析 ...................................................................... 48
4.2.1. 有線網路環境測試 ........................................................................... 49
4.2.2. 無線網路環境測試 ........................................................................... 51
4.2.3. 誤判率測試 ....................................................................................... 54
4.2.4. 綜效辨識率 ....................................................................................... 58
第五章 結論與未來展望 ...................................................................................... 59
5-1 結論 .......................................................................................................... 59
5-2 未來展望 .................................................................................................. 59
參考文獻 .............................................................................................................. 61

[1]. M.Kirby,Sirovich L., “Application of the Karhunen-Loeve procedure for characterization of human faces”,IEEE Trans,Part.Anal,Mach,Intell,12.
[2]. M.Turk,Pentlad A., “Eigenfaces for Recognition”, Journal of Cognitive Neuroscience, vol.3, no. 1, pp. 71-86, 1991.
[3]. L.F.Chen, “A New LDA-based Face Recognition Sytem Which Can Solve The Small Sample Size Problem”,Patern Recognition,vol. 33, pp. 1713-1726, 2000
[4]. Volker Blanz,Thomas Vetter, “A Morphble Model For the Synthsis of 3D Faces” SIGGRAPH’99, pp. 187-194, 1999
[5]. V.Blanz, Sami Romdhani,and Thimas Vetter, “Face Identification across different Poses and Illuminations with a 3D Morphable”, IEEE International Conference on Autoatic Face and Gesture Recognition pp.202-207, 2002
[6]. K. Lee, J. Ho, and D. Kriegman, “Acquiring linear subspaces for face recognition under variable lighting,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 27, no. 5, pp. 684-698, 2005
[7]. John Canny, “A Computational Approach to Edge Detection,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 8, no. 6, pp. 679-698, Nov. 1986.
[8]. Ying-Li Tian; Kanade, T.; Cohn, J.F., “Evaluation of Gabor-wavelet-based facial action unit recognition in image sequences of increasing complexity, ” IEEE International Conference on, vol., no., pp.229-234, 21 May 2002
[9]. Rainer Lienhart,“An Extended Set of Haar-like Features for Rapid Object Detection”IEEE International Conference on Image Processing, vol.1, no., pp.900-903, Feb 2002
[10].Pearson, Karl, “On Lines and Planes of Closest Fit to Systems of Points in Space.” Philosophical Magazine, Series 6, 2(11), pp. 559–572, 1901.
[11].Jian Yang and D. Zhang,“Two-dimensional PCA: a new approach to appearance-based face representation and recognition.”IEEE Computer Society, vol.26, pp. 131-137, 1,Jan., 2004.
[12].Wei Xu, Tao Bing Jie, Feature Fusion Based On 2DPCA and Its Application. Computer Engineering and Application, pp. 70-72, 2008.
[13].Parinya Sanguansat,“Face Hallucination Using Bilateral-Projection-Based Two-Dimensional Principal Component Analysis.” IEEE, pp. 876-880, 20-22, Dec. 2008.
[14].Baron RJ. “Mechanisms of Human Facial Recognition,” International Journal of Man-Machine Studies, pp.137–178, 1981.
[15].M. A. Turk and A. P. Pentland, “Face recognition using eigenfaces,” 1991 IEEE Conference on Computer Vision and Pattern Recognition, pp. 586-591, 1991.
[16].P.N Belhumeur, J.P. Hespanha, and D.J. Kriegman, “Eigenfaces vs. Fisherfaces: recognition using class specific linear projection,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 19, no. 7, pp. 711-720, 1997.
[17].M. Kirby, L. Sirovich, “Application of the Karhunen-Loeve Procedure for the Characterization of Human Faces,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 12, no. 1, pp. 103-108, 1990.
[18].Tan, X., and Triggs, B., “Enhanced local texture feature sets for face recognition under difficult lighting conditions,” IEEE Transactions on Image Processing, vol. 19, no. 6, pp. 1635-1650, 2010.
[19].K. Pearson, “On line and planes of closest fit to systems of points in space”, Philosophy Magazine, 2, pp.559-572, 1901.
[20].Hotelling, H., “Analysis of a Complex of Statistical Variables into Principal Components,” Journal of Educational Psychology, vol. 24, pp.498-520, 1933.
[21].R.A. Fisher, “The Statistical Utilization of Multiple Measurements”, Annual Eugenics, vol. 8, pp.376-386, 1938.
[22].W.S. Lee, H.J. Lee, J.H. Chung, “Wavelet-based FLD for facerecognition,” Proceedings of 43rd Circuits and Systems, vol. 2, pp.734-737, 2000.
[23].Nick Roussopoulos, Stephen Kelley, and Frederick Vincent., “Nearest neighbor queries,” Proceedings of the 1995 ACM SIGMOD International Conference on management of data, vol. 24, no. 2, pp.71-79, 1995.
[24].M. Mullin and R. Sukthankar, “Complete cross-validation for nearest neighbor classifiers,” Proceedings of the Seventeenth International Conference on Machine Learning, pp.639 -646, 2000.
[25].Hao Tang; Huang, T.S., “3D facial expression recognition based on automatically selected features, ” IEEE Computer Society Conference on , vol., no., pp.1,8, 23-28 June 2008
[26].Ebied, H.M., “Feature extraction using PCA and Kernel-PCA for face recognition,” Informatics and Systems (INFOS), 2012 8th International Conference on , pp.72-77, 14-16 May 2012
[27].Ming-Hsuan Yang; Kriegman, D.; Ahuja, N., “Detecting faces in images: a survey, ”, IEEE Transactions on , vol.24, no.1, pp.34,58, Jan 2002
[28].秦璿祐,“植基於二元二維主成份分析之人臉辨識”, 碩士論文, 國立勤益大學, 2011