摘要
本論文主要目的在介紹以低成本方式來實作視線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。而視線追蹤系統的應用很廣，可應用於醫護，軍事，娛樂等。本論文將實現於在複雜背景中執行視線追蹤的工作。有幾種視線追蹤的方式是利用光線反射原理、眼動圖資訊（Electro- OculoGraphy，EOG）或穿戴特殊隱形眼鏡等，其缺點可能包含高複雜度運算、高成本或者具有侵入性質。我們主要目的是為了使操作者能使用眼睛選取感興趣的目標，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。 本論文提出的視線追蹤演算法概分為四大部份，首先，使用 Haar-like Feature 人臉偵測演算法，用來分離以及定位使用者的人臉位置，接著運用樣本比對方法找出人眼粗略部位，進而使用Project演算法以及圓偵測定位眼球大小和瞳孔中心點，最後使用眼白資訊推論以及T字模型推論人眼凝視方向。
並列摘要
The objective of thesis is to present a set techniques integrated into a low-cost eye gaze tracking system. An eye gaze tracking system is a system that can estimate the direction and a position of the human eye gaze. That is, it finds where a person looks. Although the eye gaze tracking system has many potential applications, it can be used in medical, military, entertainment, etc. In this thesis will achieve eye gaze tracking in complex background. There are several ways of tracking the direction of the eye-gaze by using reflection of light, Electro- OculoGraphy（EOG）, or contact lens, etc. Each of them has its own advantages and disadvantages such as high complexity, high cost, and invasive way. User can chose the things with eyes which is they have interested in is our principle purpose. Price and convenience are two important considerations, and therefore we proposed the method not only easy to use but also to install a web camera device then it can be operated. In this thesis, four-stages algorithm are proposed to estimate the eye gaze direction. At the first stage, the face detection is use the efficient Haar-like Feature to locate the user’s face. Then eye detection is based on Template Matching. After this, the projection function and circle detection can find the eyes ball and pupil center. Finally, we will know the gazing direction by eyes of white information and T-module.
參考文獻
[1] M. Betke, J. Gips and P. Fleming, “The camera mouse: Visual tracking of body feature to provide computer access for people with severe disabilities,” IEEE Trans. on Neural Systems and Rehabilitation Engineering, vol. 10, no. 1, pp. 1-10, 2002.
[2] Y. Ebisawa, “Realtime 3D position detection of human pupil,” IEEE Symposium on Virtual Environments, Human-Computer Interfaces and Measurement Systems (VECIMS), pp. 8-12, Jul. 2004.
[3] C. H. Morimoto, D. Koons, A. Amit, M. Flickner and S. Zhai, “Keeping on eye for HCI,” XII Brazilian Symposium on Computer Graphics and Image Processing 1999. Proceedings, pp. 171-176, 1999.
[4] L. Young and D. Sheena, “Survey of eye movement recording methods,” Behavior Research Methods and Instrumentations, vol. 7, no. 5, pp. 397-429, 1975.
[5] D. Kumar and E. Poole, “Classification of EOG for human computer interface,” in the Second Joint EMBS/BMES Conference, vol. 1, pp. 64-67, Oct. 2002.