臺灣博碩士論文加值系統

電腦視覺已經是目前生活上一個不可或缺的一環，在大眾生活上已經有許多 實例可以透過電腦視覺來完成某些事情，乃至海關人臉辨識系統、etc 車牌辨識系 統到半導體產業的製程上，也需要依靠電腦視覺來辨識積體電路上的瑕疵，透過鏡 頭能夠幫我們洞悉不一樣的視覺領域，本論文主題將透過 OpenCV 來實作人臉辨 識系統，透過一些數學上的模型，進一步了解 OpenCV 辨識的原理，並搭配人臉資 料庫來做資料測試。

Computer vision has become an indispensable part of life. There are many examples in public life with computer vision. From the customs face recognition system to the etc license plate recognition system. Even the manufacturing process of the semiconductor industry, it is also necessary to rely on computer vision to identify defects on the integrated circuit. Through the lens, it can help us to understand the different visual fields. The theme of this thesis will be to implement a face recognition system through the Computer Visual Library (OpenCV). Explain some mathematical models to learn more about the principles of Computer Visual Library (OpenCV), and use the face database to do some recognition testing.

摘要 i
ABSTRACT ii
目錄 iii
表目錄 v
圖目錄 vi
第 1 章 緒論 1
1.1 研究背景 1
1.2 研究動機 1
1.3 方法簡述 2
1.4 論文架構 3
第 2 章 OpenCV 影像辨識相關研究文獻探討 4
2.1 色彩空間 4
2.2 邊緣檢測 4
2.2.1 Sobel算子 5
2.2.2 Canny算子 6
2.3 哈爾特徵分類演算法 8
第 3 章 OpenCV影像辨識實作 10
3.1 環境架構 10
3.2 辨識演算法流程 10
3.3 影像前處理 12
3.3.1 色彩空間轉換 12
3.3.2 調整次像素大小 13
3.4 邊緣偵測 14
3.5 Sobel與Canny比較結論 15
第 4 章 人臉偵測及辨識效果 17
4.1 人臉辨識程式流程圖 17
4.2 偵測人臉 18
4.3 建立人臉辨識資料庫 19
4.4 像素參數比較及人臉偵測程式測試 21
4.4.1 人臉辨識成功辨識率 21
4.4.2 在成功辨識的人臉中，辨識人臉平均所花費的時間。 24
第 5 章 結論 25
參考文獻 26

[1] Abdul Rauf Baig; Hajira Jabeen, "Big data analytics for behavior monitoring of students," in Procedia Computer Science, Riyadh, Saudi Arabia, 2016.
[2] Ramesh Jain, Rangachar Kasturi, Brian G. Schunck, MACHINE VISION, McGraw-Hill, Inc., 1995.
[3] M.A. Turk ; A.P. Pentland, "Face recognition using eigenfaces," in 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Maui, HI, USA, USA, 1991.
[4] AndrewBudiProov, "Facing the future: the impact of Apple FaceID," Biometric Technology Today, pp. 5-7, 1 2018.
[5] OpenCV, "OpenCV," [Online]. Available: https://opencv.org/.
[6] R. T. Azuma, "A survey of augmented reality," Presence: Teleoperators and Virtual Environments, pp. 355-385 , 8 1997.
[7] EmguCV,"EmguCV,"[Online]. Available: http://www.emgu.com/wiki/index.php/Main_Page.
[8] C. Poynton, "Color FAQ," 2006.
[9] T. Lindeberg, "Edge detection and ridge detection with automatic scale selection," in Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Francisco, CA, USA, USA, 1996.
[10] Sobel, Irwin; Feldman, G., "An Isotropic 3x3 Image Gradient Operator," Stanford Artificial Intelligence Project (SAIL), 1968.
[11] S. Kim, “Applications of Convolution in Image Processing with MATLAB,” University of Washington, 2013.
[12] "Performing Convolution Operations," APPLE, 2016. [Online].
[13] J. Canny, "A Computational Approach to Edge Detection," IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 679 - 698, 11 1986.
[14] Robert A.HummelB.KimiaSteven W.Zucker, “Deblurring Gaussian blur,” Computer Vision, Graphics, and Image Processing, pp. Volume 38, Issue 1, Pages 66-80, April 1987.
[15] C.P. Papageorgiou ; M. Oren ; T. Poggio, "A general framework for object detection," Bombay, India, India, 1998.
[16] P. Viola ; M. Jones, "Rapid object detection using a boosted cascade of simple features," in Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition., Kauai, HI, USA, USA, 2001.
[17] Franklin C. Crow, "Summed-area tables for texture mapping," in ACM SIGGRAPH Computer Graphics, New York, NY, USA, 1984.
[18] Yido Koo ; Wonchan Kim, "An image resolution enhancing technique using adaptive sub-pixel interpolation for digital still camera system," IEEE Transactions on Consumer Electronics, pp. 118 - 123, 2 1999.
[19] "阿洲的程式教學," [Online]. Available: http://monkeycoding.com/.