本論文主要目的在介紹如何以低成本方式來實作人眼追蹤系統以及相關的整合技術，運用此套系統可以估算出人眼凝視的方向及位置。而人眼追蹤的應用很廣，其中可應用於幫助殘障者。對於患有肌肉萎縮性脊髓側索硬化症、大腦麻痺、肢體或臉部肌肉無法行動的患者，如果本身的眼睛器官仍然能夠活動自如，患者就可以依賴此追瞳控制系統獲得獨立自主的溝通及控制能力。有幾種人眼追尋的方式是利用光線反射原理、眼動圖資訊(electrooculogram，EOG)或穿戴特殊隱形眼鏡等，其缺點可能包含高複雜度運算、高成本或者具有侵略性質。我們主要目的是為了協助傷殘者更容易操作電腦，並且考慮到價錢以及操作的難易度是兩大阻礙，因此所提出的演算系統不僅操作簡單，而且只需要額外使用一部web camera偵測裝置就能運作。我們提出的人眼偵測演算法概分為五大部份，首先，使用高效率的彩色膚色過濾器，用來分離以及定位使用者的人臉位置，接著運用三個主要求得眼特徵的投影機制將其整合並找出人眼粗略部位，進而使用FCM 演算法定位瞳孔中心點，使用
fuzzy 推論以及九個推論規則計算人眼凝視方向，並將其應用於人機介面的操作。實驗結果證明了此方法不僅快速而且能夠有效率的在複雜背景、移動人臉中執行人眼追尋工作。

The objective of this thesis is to present a set of techniques integrated into a low-cost eye gaze tracking system. An eye gaze tracking
system is a system that estimate the direction of the human’s eye gaze. That is, it finds where a person looks. Although the eye gaze tracking system has many potential applications, one of its main applications is to help the physically and vocally disabled. For some disabled persons, an extreme disability such as severe cerebral palsy or amyotrophic lateral
sclerosis (ALS) deprives them of the use of their limbs and facial muscles.If eye motion is unaffected, the person could rely on an eye gaze tracking system to attain or regain some degrees of independent communication and control. There are several ways of tracking the direction of the
eye-gaze by using reflection of light,electrooculogram (EOG), or contact
lens, etc. Each of them has its own advantages and disadvantages such as high complexity, high cost, and invasive way. Since the main application of the proposed system is to help the disabled to manipulate computers more easily, price and complexity are the two chief considerations. The proposed system consists of only one low-cost web camera which is
located directly above the center of the display screen. A five-stage algorithm is proposed to estimate the eye gaze direction. At the first stage,an efficient face detection filter based on the skin color is employed to locate the user’s face. Then three projection histograms are integrated to find the eyes. After this, the FCM algorithm is employed to locate the pupils. Then the eye gaze direction is computed by inferencing a simple fuzzy systems consisting of 9 fuzzy rules. Finally, the computed eye gaze
directions are used to manipulate the computer. Several experiments were used to test the performance of the prototype system.

[1] J. C. Wu, “人臉特徵自動抽取之演算法設計與應用,
“ URL:http://datas.ncl.edu.tw/theabs/1/, 2001.
[2] The Champion database, URL:http://www.libfind.unl.edu/alumni/
events/breakfast for champions.html.
[3] A. Kappor, “Real-time, fully automatic upper facial feature tracking,
“Proceedings of The 5th International Conference on Automatic Face
and Gesture Recognition 2002, Washington D. C, May20-21, 2002.
[4] A. M. Alattar and S. A. Rajala, “Facial Features Localization In
Front View Head and shoulders images,
“ URL:http://www.telecom.tuc.gr/paperdb/icassp99/PDF/AUTHOR/
IC992272.PDF.
[5] B. Martinkauppi, M. Laaksonen, M. Soriano, "Behavior of skin color
under varying illumination seen by different cameras at different
color spaces, " Machine Vision Applications in Industrial Inspection
IX, Martin Hunt, Editor, Proceedings of SPIE Vol. 4301 102-112,
2001.
[6] C. H. Morimoto and M. Flickner, “Real-time multiple face detection
using active illumination,” Proc. The 4th Intl. Conf. On Automatic
Face and Gesture Recognition, pp. 1-6, March 2000.
[7] C. Garcia, G. Zikos, G. Tziritas, “Face Detection in Color Images
using Wavelet Packet Analysis, “ Proceedings of the 6th IEEE
International Conference on Multimedia Computing and Systems,
Florence, pp. 703-708, 1999.
[8] G. Wyszecki and W. S. Stiles, ”Color science, ”John Wiley & Sons,
Inc, 1967.
[9] F. Du, “Human Skin Detection Using Color Segmentation,
“URL:https://courseware.vt.edu/users/abbott/5554/SkinReport.pdf
[10] H. Kashima, H. Hongo, K. Kato, and K.Yamamoto, ”A robust iris
detection method of facial and eye movement, ”Proc. Vision
Interface 2001, pp.9-14, Canada, 2001, 6.
[11] H. M. El-Bakry, “Human iris detection for information security
using fast, “ URL:http://www.wbmt.tudelft.nl.
[12] H. S. Hong, D. H. Yoo, M. J. Chung, “Real-time face tracker using
ellipse fitting and color look-up table in irregular illumination,
“ URL: http://hwrs.kaist.ac.kr/english/Sub/4/01/Newsletter/Vol3
[13] J. Tang, S. Kawato, J. Ohya, ”Face detection from a complex
background, ”Proceeding of International Workshop on Very Low
Bitrate Video Coding,Kyoto Research Park on Oct. 29-30, 1999,
JAPAN.
[14] J. C. Bezdek, “Fuzzy mathematics in pattern classification,” Ph. D
Thesis, Cornell University, 1973.
[15] J. C. Dunn, “A fuzzy relative of the ISODATA process and its use in
detecting compact, well separated clusters, “ Journal Cybern., vol. 3,
no. 3, pp. 35-57, 1973.
[16] J. M. Park, C. G. Looney, and H. C. Chen, “Fast connected
component labeling algorithm using a divide and conquer technique,
“ URL:http://cs.ua.edu/TechnicalReports/TR-2000-04.pdf.
[17] J. W. Davis, “Recognizing movement using motion histograms, ”
Technical Report No. 487, MIT Media Laboratory Perceptual
Computing Section, April 1998. 53.
[18] M. Xu, T. Akatsuka, “Detecting head pose from stereo image
sequence for active face recognition, ”AFGR98 (82-87). IEEE Top
Reference. BibRef 9800, 1998.
[19] M. Ikeda, H. Ebine and O. Nakamura, “Extraction of faces of more
than one person from natural background for personal identification,
" 2001 IEEE Canadian Conference on Electrical and Computer
Engineering, Vol. I, pp.323-328, 2001-5.
[20] N. Barrett and A. Chalmers, “Visual Stereoscopic Eye Tracking,
“URL:http://www.manukau.ac.nz/departments/e_e/research/nb.pdf
[21] R. C. K. Hua, L. C. D. Silva and P. Vadakkepat, “Detection and
tracking of faces in real environments, ” accepted to publish in the
proceedings of The 2002 International Conference on Imaging
Science, Systems, and Technology (CISST''02), to be held in Las
Vegas, USA, June 24-27, 2002
[22] R. L. Hsu, M. A. Mottaleb, and A. K. Jain, “Face detection in color
images,” IEEE Trans. Pattern Analysis and Machine Intell., 24:
696706, 2002.
[23] R. S. Feris, T. E. Campos, and R. M. Cesar, ”Detection and tracking
of facial features in video sequences, ” Proc. Mexican International
Conference on Artificial Intelligence, pages 129-137, 2000.
[24] R. Lengagne, P. Fua, and O. Monga, “3D Face Modeling from Stereo
and Differential Constraints, ” Proc. IEEE International Conference
on Automatic Face and Gesture Recognition, Nara, Japan, April
1998.
[25] S. H. Yeh, “Human facial animation based on real image sequence, ”
URL:http://sun.lib.nsysu.edu.tw/ETD-db/etd-0724101-163439.pdf,
2001.
[26] S. Baskan, M. M. Bulut and V. Atalay, “Projection based method for
segmentation of human face and its evaluation”, Pattern
Recognition Letters, Vol.23, No.14, pp. 1623-1629, 2002.
[27] S. Kawato and J. Ohya, ”Two-step approach for real-time eye
tracking with a new filtering technique, ” Proc. Int. Conf. on
System, Man & Cybernetics, pp. 1366-1371, 2000.
[28] Y. S. Chen, C. H. Su, J. H. Chen, C. S. Chen, Y. P. Hung, and C. S.
Fuh, "Video-based eye tracking for auto stereoscopic displays, "
Optical Engineering, vol. 40, no. 12, pp. 2726--2734, Dec. 2001.
[29] Y. Nakanishi, T. Fujii, K. Kiatjima, Y. Sato, H. Koike, “Vision-based
face tracking system for large displays, “ The Fourth International
Conference on Ubiquitous Computing, 2002.
[30] Z. Liposcak and S. Loncaric, “Prediction and verification for face
detection, “ Proceedings of the First Int’l Workshop on Image and
Signal Processing and Analysis, pp. 107-111, Pula, Croatia, 2000.