5.1 結論
本研究提出一個使用筆記型電腦內建之單一攝影機的即時注視區域分析方 法，由人臉五官位置的分布，利用啟發式規則針對眼睛搜尋區域做適當的縮 減，除了加速偵測眼睛的速率外，亦有助於提高 Adaboost 眼睛偵測的準確率。
在找到眼睛區域後，利用瞳孔位於眼睛區域內最深色之虹膜中心的部分，以及 虹膜區域顏色為由淺而深輻射向內的特性，修改[26]之演算法，透過內積法快 速計算出瞳孔位置。最後經由本研究所提出的二階層式支持向量機，利用形狀 特徵經過第一層支持向量機所產生的區域機率值先做注視區域的初步判斷篩選 後，再由位置特徵經過第二層支持向量機做最終的注視區塊判定。
本研究提出之二階層式支持向量機除了能降低載入的訓練模型量，亦能提 高整體注視區域判定的準確度。利用本研究提出之注視區塊決策方法，平均準 確度可達 80%~84%。且較僅使用單一層支持向量機之準確度提升了約 9.4%。
5.2 應用
本研究可進一步延伸應用於醫療服務上，發展為重度肢體障礙人士的輔助 工具，例如將系統安裝置行動載具並安置於輪椅之固定位置，配合相關的應用 程式在本系統設定之九宮格上配置幾項大功能。例如向前、向後、向左、向右
之方向控制或是加裝 IP Camera 的控制功能等等，可以讓患者有更多的方式與 外界接觸，了解外界狀況。
5.3 未來研究
本研究提出之方法存在許多限制，例如在眼睛偵測及瞳孔偵測上，若是眼 睛區域受到遮蔽或是環境光線不佳的情況下，會導致偵測效果不彰；而注視區 域分析部分，由於使用的特徵皆為 2D 平面上的資訊，當使用者移動後便會失去 準確性。
未來工作在演算法部分可針對以下方向做改進，以增加本研究的實用性：
（1） 對於使用者佩戴的粗框眼鏡造成眼睛偵測失敗的部分，可加入去除眼 鏡的演算法來加以改善。
（2） 若能增加第二台攝影機，或是利用如 kinect 等能提供 3D 資訊的攝影 機來做輔助，透過景深的資訊建立真實空間的位置關係，以動態方式 調整改變模型，以達到動態注視區域分析，可降低相關之使用限制。
此外，由於本研究所使用的是筆記型電腦內建之網路攝影機，相對高階攝 影機來說是屬於解析度較低的，若能提高解析度，對於注視區域分析上也會有 顯著的幫助。
參考文獻
[1] "Studio Encoding Parameters of Digital Television for Standard 4:3 and Wide-Screen 16:9 Aspect Ratios," ed: International Telecommunication Union, 2011.
[2] 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 Transactions on Consumer Electronics, vol. 59, pp. 415-421, 2013.
[3] C.C. Chang and C.J. Lin, "LIBSVM: A Library for Support Vector Machines," ACM Transcations on Intelligent Systems and Technology, 2011.
[4] S. Chen and C. Liu, "Fast Eye Detection Using Different Color Spaces," in
IEEE Internation Conference on Systems, Man, and Cybernetics, ed.
Anchorage, AK, 2011, pp. 521-526.
[5] A. J. Colmenarez and T. S. Huang, "Face Detection with Information-Based Maximum Discrimination," in Proceedings of IEEE Conference on Computer
Vision and Pattern Recognition, 1997, pp. 782-787.
[6] I. Craw, D. Tock, and A. Bennett, "Finding Face Features," in Proceedings of
the Second European Conference on Computer Vision, 1992, pp. 92-96.
[7] Y. Dai and Y. Nakano, "Face-Texture Model Based on SGLD and Its Application in Face Detection in a Color Scene," Pattern Recognition, pp.
238-242, 1996.
[8] J. Daugman, "New Methods in Iris Recognition," IEEE Transactions on
Systems, Man and Cybernetics, vol. 37, pp. 1167-1175, 2007.
[9] D. W. Hansen and Q. Ji, "In the Eye of the Beholder: A Survey of Models for Eyes and Gaze," IEEE Transactions on Pattern Analysis and Machine
Intelligence, vol. 32, 2010.
[10] T. Kawaguchi and M. Rizon, "Iris Detection Using Intensity and Edge Information," Pattern Recognition, pp. 549-562, 2003.
[11] R. Kjeldsen and J. Kender, "Finding Skin in Color Images," in Proceedings
of the Second International Conference onAutomatic Face and Gesture Recognition, 1996, pp. 312-317.
[12] A. Lanitis, C. J. Taylor, and T. F. Cootes, "An Automatic Face Identification System Using Flexible Appearance Models," Image and Vision Computing, vol. 13, pp. 393-401, 1995.
[13] T. K. Leung, M. C. Burl, and P. Perona, "Finding Faces in Cluttered Scenes
on Computer Vision, 1995, pp. 637-644.
[14] M. S. Lew, "Informaiton Theoretic View-Based and Modular Face Detection," in Proceedings of the Second International Conference on
Automatic Face and Gesture Recognition, 1996, pp. 198-203.
[15] S. McKenna, S. Gong, and Y. Raja, "Modelling Facial Colour and Indentity with Gaussian Mixtures," Pattern Recognition, vol. 31, pp. 1883-1892, 1998.
[16] P. Moallem, B. S. Mousavi, and S. A. Monadjemi, "A novel fuzzy rule base system for pose independent faces detection," Applied Soft Computing, vol.
11, pp. 1801-1810, 2011.
[17] E. Osuna, R. Freund, and F. Girosi, "Training Support Vector Machines: An Application to Face Detection," in Proceedings. IEEE Conference on
Computer Vision and Pattern Recognition, 1997, pp. 130-136.
[18] N. Otsu, "A Threshold Selection Method from Gray-level Histograms," IEEE
Transactions on Systems, Man and Cybernetics, vol. 9, pp. 62-66, 1979.
[19] P. J. Phillips, K. W. Bowyer, and P. J. Flynn, "CASIA Iris Image Database(ver 1.0)," 2007.
[20] A. Rajagopalan, K. Kumar, J. Karlekar, R. Manivasakan, M. Patil, U. Desai,
et al., "Finding Faces in Photographs," in Proceedings. Sixth IEEE International Conference on Computer Vision, 1998, pp. 640-645.
[21] H. Rowley, S. Baluja, and T. Kanade, "Neural Network-Based Face Detection," IEEE Transactions on Pattern Analysis and Machine
Intelligence, vol. 20, pp. 23-38, 1998.
[22] H. Schneiderman and T. Kanade, "Probabilistic Modeling of Local Appearance and Spatial Relationships for Object Recognition," in
Proceedings. IEEE Conference on Computer Vision and Pattern Recognition,
1998, pp. 45-51.[23] W. Sewell and O. Komogortsev, "Real-Time Eye Gaze Tracking With an Unmodified Commodity Webcam Employing a Neural Network," in Human
Factors in Computing Systems (CHI), 2010.
[24] K.K. Sung and T. Poggio, "Example-Based Learning for View-Based Human Face Detection," IEEE Transactions on Pattern Analysis and Machine
Intelligence, vol. 20, pp. 39-51, 1998.
[25] Y. L. Tian, T. Kanade, and J. F. Cohn, "Dual-State Parametric Eye Tracking,"
presented at the IEEE International Conference on Automatic Face and Gesture Recognition, 2000.
[26] F. Timm and E. Barth, "Accurate Eye Centre Localisation by Means of Gradients," in Proceedings of the Int. Conference on Computer Vision Theory
and Applications, Algarve, Portugal, 2011, pp. 125-130.
[27] M. Turk and A. Pentland, "Eigenfaces for Recognition," Cognitive
Neuroscience, vol. 3, pp. 71-86, 1991.
[28] P. Viola and M. J. Jones, "Robust Real-Time Face Detection," International
Jounrnal of Computer Vision, vol. 57, pp. 137-154, 2004.
[29] G. Yang and T. S. Hung, "Human Face Detection in Complex Background,"
Pattern Recognition, vol. 27, pp. 53-63, 1994.
[30] J. Yang and A. Waibel, "A Real-Time Face Tracker," in Proceedings Third
IEEE Workshop on Applications of Computer Vision, 1996, pp. 142-147.
[31] M.H. Yang, D. J. Kriegman, and N. Ahuja, "Detecting Faces in Images: A Survey," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 24, pp. 34-58, 2002.
[32] K. C. Yow and R. Cipolla, "Feature-Based Human Face Detection," Image
and Vision Computing, vol. 15, pp. 713-735, 1997.
[33] 許雅淳, "Gaze Estimation Using Single Webcam," Master, National Taiwan Normal University, 2013.