影像追蹤在現今講求方便與安全的時代扮演著相當重要的角色，像眼控滑鼠、駕駛疲倦偵測等便是應用影像追蹤技術的一些例子。

本篇論文中，主要的目的是追蹤使用者之雙眼位置並且判斷眼睛的狀態為睜開或是閉上。而在本文之前，已經有許多學者針對眼睛的追蹤做了許許多多不同的研究，但大部份的學者都是針對裸視使用者進行研究，而對於佩戴眼鏡使用者卻甚少著墨。眼鏡帶給偵測與追蹤的影響甚鉅，主要以鏡框干擾以及鏡面反光造成的影響最大。

本篇研究採用主動式輪廓擷取鏡框邊緣，將鏡框排除在搜索範圍外，降低有邊鏡框對偵測造成的影響，並且限定在搜索範圍內使用眼睛遮罩定位眼睛搭配可變型樣板輔助定位，減少鏡片反光對偵測的影響。在追蹤的流程方面，我們利用眼鏡鏡框外形的不變性，建立中心鏡框區塊作為追蹤的依據搭配區塊匹配演算法進行追蹤，最後，再對眼睛之睜眼與閉眼狀態作評估,實驗結果顯示所提出的方法對於追蹤眼睛以及狀態判斷結果是有效的。

The role of image tracking today has become much more important for both convenience and security issues. A few of examples using image tracking technique are eye mouse system and driver fatigue detection.

In this thesis, our main purpose is to track the location of human eyes and to detect the state of eyes, which can be open or closed. Many researches had investigated the problem of eye tracking. Most of them developed their systems only for naked eye users.(i.e. users without wearing eyeglasses). When a person wears eyeglasses, however, the eyeglasses result in high inaccuracy for eye detection and tracking, mainly from eyeglasses frame and reflection of lens.

We propose a method that excludes eyeglasses frame from search area of eyes by using active contour. In the eye detection step, we use eye mask and deformable template to detect eyes within search area, which is determined by active contour. Active contour has good benefit to get edge of frame. It will help us to reduce effect of eyeglasses frame and reflection of lens. We use block matching algorithm on central eyeglasses block for our tracking strategy, taking advantage of the fact that the shape of eyeglasses is fixed. Finally, eye state will be determined after we track the position of eyes. Experiment show that our method can effectively track eyes and detect eye state.

[1] R.C. Gonzalez, R.E. Woods, Digital Image Processing, ed., Prentice Hall, 1987.

[2] 范國清、王元凱、陳炳富，”追蹤演算法(Survey of Tracking Algorithms)”，影像與識別2002,Vol.8 No.4

[3] D. Chai and K.N, Ngan, “Face segmentation using skin color map in videophone applications,” IEEE Transactions on Circuits and systems for Video Technology, U.S.A., vol.9, no.4, pp.551-563, Jun 1989.

[4] Stan Birchfield, “An Elliptical Head Tracker,” Asilomar Conference on Signals, Systems, and Computers, vol.2, pp: 1710 – 1714, Nov 1997.

[5] Donna J. Williams, Mubarak Shah, “A Fast Algorithm for Active Contours” Computer Vision, pp.592 – 595, Dec. 1990.

[6] Alan L. Yuille, David S. Cohen, Peter W. Hallinan, ”Feature extraction from faces using deformable templates,” Computer Vision and Pattern Recognition, pp:104 – 109, Jun 1989.

[7] Zhichao Tian, Huabiao Qin, ”Real-time Driver’s Eye State Detection,” IEEE International Conference on vehicular electronics and safety, pp: 285 – 289, Oct. 2005.

[8] Yong-Sheng Chen,Chan-Hung Su, Jiun-Hung Chen, Chu-Song Chen,Yi-Ping hung, Chiou-Shann Fuh, ”Video-based Eye Tracking for Autostereoscopic Displays,” Optical Engineering, vol.40, no.12, pp: 2726-2734, Dec.2001.

[9] Chang-Hsing Lee, Ling-Hwei Chen, ”A Fast Motion Estimation Algorithm Based on the Block Sum Pyramid,” IEEE Transactions on Image Processing, vol.6, no.11, Nov.1997.

[10] T. KOGA, K. IINUMA, A. HIRANO, Y. IIJIMA, T. ISHIGURO , ”Motion-compensated interframe coding for video conferencing” Proceedings NTC'81 (IEEE), pp: G.5.3.1 - G.5.3.4

[11] Shan Zhu, Kai-Kuang Ma, ”A New Diamond Search Algorithm for Fast Block-Matching Motion Estimation,” IEEE Transactions on Image Processing, vol.9, no.2, Feb.2000.

[12] Zeeshan Hameed Khan, Muhammad Aurangzeb, “Real Time Object Tracking Using BMA,” Information and Communication Technologies ICICT 2005, pp: 79 – 83, Aug. 2005.

[13] Andrew Blake, Michael Isard, ”Active Contours,” Springer-Verlag London 1998

[14] Shinjiro Kawato, Jun Ohya, “Two-step Approach for Real-time Eye Tracking with a New Filtering Technique,” IEEE International Conference, vol.2,
pp: 1366 - 1371, Oct. 2000.

[15] 杜兆乘， “視訊中基於眉毛之眼睛追蹤與閉眼偵測,” 國立台灣科技大學，電子工程研究所，碩士學位論文，2007。

[16] Kap-Ho Seo, Ju-Jang Lee, “Real-Time Object Tracking and Segmentation Using Adaptive Color Snake Model,” Industrial Electronics Society, IECON, pp: 1902-1906, Nov. 2005.

[17] Boo Hwan Lee, Il Choi, Gi Goon Jeon, “Motion-Based Moving Object Tracking using an active contour,” Acoustics, Speech and Signal Processing, 2006. ICASSP 2006 Proceedings, vol.2, May 2006.

[18] Won Kim, Sun-Gi Hong, Ju-Jang Lee, “An Active Contour Model using Image Flow for Tracking a Moving Object,” Intelligent Robots and Systems, . IROS '99, vol.1, pp: 216 - 221, Oct. 1999.

[19] Yunchuan Geng, Yangxing Liu, Satoshi Goto, Takeshi Ikenaga, “Real-Time Automatic Moving Object Extraction and Tracking Based on Improved Active Contour Model,” Intelligent Signal Processing and Communication Systems, ISPACS, pp: 149 – 152, Dec 2005.

[20] 張凱傑，“眼控與頭控之人機介面系統研發與整合”，逢甲大學自動控制工程研究所碩士論文，民國九十年。

[21] 陳彥良，“即時立體視覺物體追蹤系統”，中原大學，機械工程學系，碩士學位文，2001。

[22] H. Rowley, S. Baluja, and T. kanade, “Neural Network-Based Face Detection,” IEEE Trans. PAMI, vol.20, no.2, pp: 23-38, June. 1998.

[23] Zhiwei Zhu, Qiang Ji, “Robust Real-time Eye Detection and Tracking Under Variable Lighting Conditions and Various Face Orientations,” Computer Vision and Image Understanding, vol.38, no.1, pp: 124-154, 2005.

[24] Son Lam Phung, Abdesselam Bouzerdoum, and Douglas Chai, “A Novel Skin Color Model in YCbCr Color Space and its Application to Human Face Detection,” Image Processing. vol.1, pp: I-289 - I-292, Sept. 2002.

[25] Iain E. G. Richardson, “H.264 and MPEG-4 Video Compression: Video Coding for Next-generation Multimedia,” WILEY, 2003.