現今，絕大多數的人機介面皆透過鍵盤、滑鼠或觸控裝置等接觸式裝置來控制與互動。如何讓裝置主動地分析人類的行為表現，並提供人類所需求的服務以達到非接觸式的互動，將會是人機互動的未來趨勢。非接觸式的人機介面可藉由瞳孔偵測系統來達成。瞳孔偵測系統是希望透過影像處理的方法，從攝影機所擷取的影像進行瞳孔偵測，並且根據偵測的結果進一步分析出使用者雙眼的開闔狀態。
人臉偵測的功能是藉由影像處理來進行的典型人機互動方式。本研究以人臉偵測為基礎，更進一步地發展出瞳孔偵測系統。在使用傳統的人臉偵測系統時，使用者必須臉部正對攝影機才能使系統正常運作。這個限制造成使用者在操作上有些不自然。本篇論文中提出可以對平面旋轉的人臉進行偵測的架構。架構中，首先利用膚色偵測定位出人臉候選區並針對候選區進行邊緣偵測，接著套用放射性模板進行邊緣特徵的搜尋。根據放射性模板的特徵搜尋結果可以將平面旋轉的人臉校正為正常(up-right)角度，後續使用一個正常(up-right)角度的人臉偵測模組對該候選區進行人臉驗證。經由上述的步驟後，將人臉影像進行力矩權重定位法擷取出眼部區域，並且由YUV色彩空間過濾出瞳孔的最終位置。藉由這個系統架構，使用者可以更加自然、直覺地操作系統。

Nowadays, most of man-machine interfaces are controlled by contact devices such as keyboard, mouse, or touch panel. It will be a future trend of man-machine interface to analyze human behaviors and provide suitable services through contactless interfaces instead of contact interfaces. Man-machine contactless interface can be achieved by pupils detection system. Pupils detection system can detect user’s pupils from the input image by camera and further analyze user’s eyes status (close or open). Then, the pupils detection system can play a key role in contactless man-machine interface.
Face detection conducted by image processing is a crucial part of man-machine interaction. This research is on the basis of face detection to develop a pupils detection system. In the typical face detection system, users need to face the camera without head tilting to make the system operate normally and accurately. Due to this limitation, it is inconvenient in the real practical applications. This research proposes a point-rotation face detection framework. In this framework, we first locate the face candidates by skin tone detection and apply the edge detection on the candidates to complete the localization. Then we search the edge features by radial template. By the symmetricity of faces, our method can correct the face image to the up-right angle. Finally, a frontal face detector is used to determine the existence and the location of faces. After the previous process the face image will be converted to an up-right face image. Then we apply the torque-weight method to extract the eyes region on the face image. At last, the pupils in the eyes region are detected by using YUV color space. By the proposed framework, the users can operate the system more instinctively and easily.

[1]. Christophe Garcia and Georgios Tziritas, “Face Detection Using Quantized Skin Color Regions Merging and Wavelet Packet Analysis,” IEEE Transactions on Multimedia, Vol. 1, No. 3, pp. 264-277, 1999.
[2]. Constantine P. Papageorgiou, Michael Oren, Tomaso Poggio, “A General Framework for Object Detection,” IEEE Sixth International Conference on Computer Vision, pp. 555-562, 1998.
[3]. Paul Viola and Micheal Jones, “Rapid Object Detection Using a Boosted Cascade of Simple Features,” IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Vol. 1, pp. 511-518,2001.
[4]. Cha Zhang and Zhengyou Zhang, “A Survey of Recent Advances in Face Detection,” Microsoft Research, 2010.
[5]. Bo Wu, Haizhou Ai, Chang Huang, Shihong Lao, “Fast Rotation Invariant Multi-View Face Detection Based on Real Adaboost,” IEEE International Conference on Automatic Face and Gesture Recognition, pp. 79-84, 2004.
[6]. Duan-Sheng Chen and Zheng-Kai Liu, “Generalized Haar-Like Features for Fast Face Detection,” IEEE International Conference on Machine Learning and Cybernetics, Vol. 4, pp. 2131-2135, 2007.
[7]. Qi Han, Qiong Li, Xiongdong Huang, Tong Zhou and XiaMu Niu, “Eyes Tracking in a Video Sequence Based-On Haar-like Features and Skin Color,” IEEE Third International Conference on Intelligent Information Hiding and Multimedia Signal Processing, Vol. 1, pp. 608-611, 2007.
[8]. Cheng-Chin Chiang, Wen-Kai Tai, Mau-Tsuen Yang, Yi-Ting Huang and Chi-Jaung Huang,“ A Novel Method for Detecting Lips, Eyes and Faces in Real Time,” Real-Time Imaging, Vol. 9, pp. 277-287, 2003.
[9]. Xiao-Guang Lv, Jie Zhou and Chang-Shui Zhang, “A Novel Algorithm for Rotated Human Face Detection,” IEEE Conference on Computer Vision and Pattern Recognition, Vol. 1, pp. 760-765, 2000.
[10]. Heng Liu, Shengye Yan, Xilin Chen and Wen Gao, “Rotated Face Detection in Color Images Using Radial Template (RT),” IEEE International Conference on Multimedia and Expo, Vol. 3, pp. 137-140, 2003.
[11]. Lienhart Rainer, Maydt Jochen, “An Extended Set of Haar-like Features for Rapid Object Detection,” IEEE International Conference on Image Processing, Vol. 1, pp. 900-903, 2002.
[12]. Lifeng He, Yuyan Chao, Kenji Suzuki and Kesheng Wu, “Fast Connected-Component Labeling,” Pattern Recognition, Vol. 42, pp. 1977-1987, 2009.
[13]. Lifeng He, Yuyan Chao and Kenji Suzuki, “A Run-Based Two-Scan Labeling Algorithm,” IEEE Transactions on Image Processing, Vol. 17, pp. 749-756, 2008.
[14]. Rowley Henry A., Baluja Shumeet, Kanade Takeo, “Rotation Invariant Neural Network-Based Face Detection,” IEEE Computer Society Conference on Computer Vision and Pattern Recognition , pp. 963-970, 1998.
[15]. Changming Sun, “Symmetry Detection Using Gradient Information,” Pattern Recognition Letters, Vol. 16, pp. 987-996, 1995.
[16]. Changming Sun and D. Si, “Fast Reflectional Symmetry Detection Using Orientation Histograms,” Real-Time Imaging, Vol. 5, pp. 63-74,1999.
[17]. Rainer Lienhart, Alexander Kuranov, Vadim Pisarevsky, “Empirical Analysis of Detection Cascades of Boosted Classifiers for Rapid Object Detection,” Pattern Recognition, Vol. 2781, pp. 297-304, 2003.
[18]. Shuo Chen and Chengjun Liu, “Fast Eye Detection Using Different Color Space,” IEEE International Conference on Systems, Man, and Cybernetics (SMC), pp. 521-526, 2011.