摘要 I
ABSTRACT III
致謝 V
目錄 VI
圖目錄 IX
表目錄 XII
第一章 、緒論 1
1.1 研究動機 1
1.2系統架構與流程 2
1.3論文架構 3
第二章 、習知相關技術 4
2.1 縮減取樣(Down-Sampling) 4
2.1.1 雙線性內插法(Bilinear Interpolation) 4
2.1.2 最近相鄰內插法(Nearest Neighbor Interpolation) 6
2.1.3 雙立方內插法(Bicubic Interpolation) 8
2.2 邊緣偵測(Edge Detection) 10
2.2.1 Roberts邊緣偵測(Roberts Edge Operator) 10
2.2.2 Prewitt邊緣偵測(Prewitt Edge Detector) 11
2.2.3 Sobel邊緣偵測(Sobel Edge Detector) 12
2.2.4 Canny邊緣偵測(Sobel Edge Detector) 12
2.3 二值化 15
2.3.1 固定式二值化 15
2.3.2 疊代法二值化(Iterative Method) 16
2.3.3大津法二值化(OTSU Method) 17
2.4 形態學(Morphology) 18
2.4.1 侵蝕(Erosion) 18
2.4.2 膨脹(dilation) 19
2.4.3 閉合、斷開(Closing、Opening) 20
2.5 影像特徵描述 20
2.5.1 LBP特徵(Local Binary Pattern) 20
2.5.2 Haar-like特徵 22
2.5.3方向梯度直方圖 (Histogram of Oriented Gradient) 23
2.6 分類器(Classifier) 26
2.6.1 Adaboost (Adaptive Boosting) 26
2.6.2 支持向量機(Support Vector Machine) 27
第三章 、相關文獻探討 30
3.1 應用支持向量機於學生上課專注度之分析 31
3.2 Face Detection in Real Time Based on HOG 35
3.3 Face-and-Clothing Based People Clustering in Video Content 38
3.4 Fast People Counting Using Head Detection From Skeleton Graph 42
3.5 Human Detection Using Depth Information by Kinect 46
3.6 Human Activity Recognition Using Sequences of Postures 50
3.7 View Invariant Human Action Recognition Using Histograms of 3D Joints 53
第四章 、教室內學生上課姿態之即時分析系統 56
4.1 影像預處理 58
4.1.1 縮減取樣 58
4.1.2 影像增強 59
4.2 上半身偵測 61
4.2.1 二值化 61
4.2.2 形態學 63
4.2.3 邊緣偵測 65
4.2.4 膚色偵測 67
4.2.5 上半身區域計算 73
4.3 上半身定位 75
4.3.1 中心點計算 76
4.3.2 距離計算 77
4.4 姿態辨識 79
4.4.1 訓練分類器 80
4.4.2 姿態分類 81
第五章 、實驗結果 83
5.1 實驗環境 83
5.2 輸出結果 84
5.3 實驗結果分析 86
5.3.1 主觀分析 86
5.3.2 客觀分析 86
5.3.3 相關方法整體性比較 87
第六章 、結論與未來方向 90
6.1 錯誤探討 90
6.2 未來方向 92
6.3 結論 92
參考文獻 94

[1]R. G. Keys, “Cubic convolution interpolation for digital image processing”, IEEE Trans. Acoustics, Speech, and Signal Processing, Vo1.29, pp.1153- 1160, 1981
[2]L. G. Roberts, “Machine perception of 3-D solids”, Optical and Electro-Optical Information Processing. MIT Press, 1965.
[3]J. M. S. Prewitt, “Object enhancement and extraction”, Picture Processing and Psychopictorics, pp. 75-149, 1970.
[4]I. Sobel, G. Feldman, “A 3x3 isotropic gradient operator for image processing”, presented at a talk at the Stanford Artificial Project, 1968.
[5]J. Canny, “A computational approach to edge detection”, Pattern Analysis and Machine Intelligence, vol. 8, 679-714, 1986
[6]Otsu, Nobuyuki. A threshold selection method from gray-level histograms. IEEE transactions on systrems, man, and cybernetics, vol. smc-9, no. 1, january 1979, PP.62-66
[7]T. Ojala, M. Pietikainen, and D. Harwood, “Performance evaluation of texture measures with classification based on Kullback discrimination of distributions”, Proceedings of the 12th IAPR International Conference on Pattern Recognition, vol. 1, pp. 582 - 585,1994.
[8]Viola, Paul, and Michael Jones,” Rapid object detection using a boosted cascade of simple features”, Computer Vision and Pattern Recognition, 2001.
[9]N. Dalal and B. Triggs, “Histograms of oriented gradients for human detection”, Computer Vision and Pattern Recognition, 2005.
[10]Y. Freund and R. E. Schapire, “A decision theoretic generalization of on-line learning and an application to boosting” , Journal of Computer and System Sciences, Vol. 55, pp. 119-139, 1997.
[11]C. Cortes and V. Vapnik, “Support-vector networks” , Machine Learning, Vol.20, pp.273-297, 1995
[12]黃登淵, 黃啟倫, 楊幃傑, “應用支持向量機於學生上課專注度之分析”, 第十六屆離島資訊技術與應用研討會, 金門, May 2017.
[13]N. Rekha and M.Z. Kurian, “Face detection in real time based on HOG”, International Journal of Advanced Research in Computer Engineering & Technology, Vol. 3, pp.1345-1352, 2014.
[14]EL KHOURY, Elie; SENAC, Christine; JOLY, Philippe” Face-and-clothing based people clustering in video content”, Proceedings of the international conference on Multimedia information retrieval, Philadelphia, Pennsylvania, USA, pp. 295-304, 2010
[15]Aziz Kheir-Eddine, et al. “Pedestrian Head Detection and Tracking Using Skeleton Graph for People Counting in Crowded Environments”, 2th IAPR Conference on Machine Vision Applications, pp.516-519, June 2011.
[16]Xia, Lu, Chia-Chih Chen, and Jake K. Aggarwal, "Human detection using depth information by kinect.", IEEE Computer Vision and Pattern Recognition Workshops (CVPRW), 2011 IEEE Computer Society Conference, pp. 15-22, June, 2011
[17]Kellokumpu, Vili, Matti Pietikäinen, and Janne Heikkilä, "Human activity recognition using sequences of postures.", MVA, Tsukuba Science City, Japan, pp. 570-573, May, 2005
[18]Xia, Lu, Chia-Chih Chen, and J. K. Aggarwal, "View invariant human action recognition using histograms of 3d joints.", IEEE Computer Society Conference, pp. 20-27, June, 2012
[19]Gasparini, F., & Schettini, R. “Skin segmentation using multiple thresholding”. Electronic Imaging 2006 International Society for Optics and Photonics, Milano, Italy, pp. 60610F-60610F,Auguest 2006
[20]G. H. Joblove and D. Greenberg, “Color spaces for computer graphics”, ACM SIGGRAPH Computer Graphics, Vol.12, pp.20-25, 1978
[21]Chai, Douglas, and Abdesselam Bouzerdoum, "A Bayesian approach to skin color classification in YCbCr color space.", IEEE TENCON 2000. Proceedings, Vol. 2, pp. 421-424, 2000