眼動儀是未來智慧型電子產品的重要人機互動介面，可以用於分析使用者的關注點以及意圖。自然光源眼動儀於眼睛定位與虹膜中心位置的計算均較紅外光眼動儀困難。但因為紅外線光源近距離照射觀看者的眼睛，長時間使用將導致眼睛疲勞，且無法在戶外太陽光下使用。反之，可見光眼動儀無須外加光源，未來有機會成為消費性電子產品的基本輸入配備。然而，因為可見光源的變化相當大，導致眼睛影像的特徵有相當的差異，使得偵測瞳孔困難，遂改以虹膜異色邊緣取代之，再計算最適合的橢圓方程式，推算眼球中心的座標，加入頭動補償資訊，修正偏移的眼球中心，最後映射到螢幕上，得知使用者的目光凝視焦點。

The gaze tracking system is designed to analyze the intentions and interests of the user. There are problems of a gaze tracking system with visible light, such as detecting the region of the pupil and accurately identifying the center of iris region, which appear to be more difficult than gaze tracking system with IR light. However, the illumination from IR light sources not only makes the user feel uncomfortable with their eyes, but fails in an outdoor environment. In contrast, the visible light gaze tracker could be operated smoothly without an extra IR light sources. It is expected the visible light gaze tracker will become a general input device integrated with the smart consumer electronics or other specific devices. However, the main challenge of visible gaze tracker is the difficulty in detecting the pupil location caused by the variations of the illumination. Instead, the system can only detect the limbus circle and estimate the center of the eyeball by fitting the model with the shape of the detected limbus circle. This study aims to compensate the error according to the information of head movement, and then calculate where the user is reading.

[1] K. N. Kim and R. S. Ramakrishna, “Vision-based eye-gaze tracking for human computer interface,” in Proc. IEEE Int. Conf. Systems, Man, and Cybernetics, vol. 2, pp. 324–329, Oct. 1999.
[2] J. Zhu and J. Yang, “Subpixel Eye Gaze Tracking,” in Proc. IEEE Int. Conf. Automatic Face and Gesture Recognition, pp. 131-136, May 2002.
[3] J. Daugman, “How iris recognition works,” IEEE Trans. Circuits Syst. Video Technol., vol. 14, no. 1, pp. 21-30, Jan. 2004.
[4] T. Moriyama, T. Kanade, J. Xiao, and J.F. Cohn, “Meticulously Detailed Eye Region Model and Its Application to Analysis of Facial Images,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 28, no. 5, pp. 738-752, May 2006.
[5] S. J. Baek, K. A. Choi, C. Ma, Y. H. Kim, and S. J. Ko, “Eyeball model-based iris center localization for visible image-based eye-gaze tracking systems,” IEEE Trans. Consumer Electron., vol. 59, no. 2, pp. 415-421, May 2013.
[6] J. Sofia Jennifer, T. Sree Sharmila and R. Srinivasan, “Facial feature extraction for head tilt images based on eye canthus,” 2016 IEEE Region 10 Conference (TENCON), Singapore, 2016, pp. 566-570.
[7] P. Viola and M. Jones, “Rapid object detection using a boosted cascade of simple features, ” in Proc. IEEE Conf Comput. Vis. Pattern Recognit. , 2001, pp. I-511–I-518.
[8] C. Harris and M. Stephens, “A combined corner and edge detector,” In 4th Alvey Vision Conference, 1988, pp. 147–151.
[9] C. Xu, Y. Zheng and Z. Wang, “Semantic feature extraction for accurate eye corner detection, ” 19th International Conference on Pattern Recognition, Tampa, FL, 2008, pp. 1-4.
[10] D. Borza and R. Danescu, “Eye Shape and Corners Detection in Periocular Images Using Particle Filters, ” 12th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS), Naples, 2016, pp. 15-22.
[11] K. Zhang, L. Zhang and M. H. Yang, “Real-time compressive tracking, ” European conference on computer vision, Berlin, 2012, pp. 864-877.
[12] W. C. Kao, C. Y. Lee, C. Y. Lin, T. Y. Su, B. Y. Ke and C. Y. Liao, “Gaze tracking with particle swarm optimization, ” 2015 International Symposium on Consumer Electronics (ISCE), Madrid, 2015, pp. 1-2.
[13] W. C. Kao, C. Y. Lin, C. C. Hsu, C. Y. Lee, B. Y. Ke and T. Y. Su, “Optimal iris region matching and gaze point calibration for real-time eye tracking systems, ” 2016 IEEE International Conference on Consumer Electronics (ICCE), Las Vegas, NV, 2016, pp. 443-444.