使用眼電位法設計眼動偵測系統與其人機介面之應用

Abstract

近年來對於重症患者的需求越來越受到重視，在人機互動介面(Human-Computer Interface, HCI)的研究領域當中如何幫助重症患者有效的與外界進行溝通一直是個重要的議題，其中在人機介面的研究當中，眼睛的移動是個相當重要的特徵。使用者可以藉由控制個人眼睛的移動來做為系統的控制訊號。然而在相關領域的研究當中，由於受限演算法的複雜度以及硬體上的限制。甚少有研究提出大眾化的設計並且考慮到在現實生活當中的可行性。因此為了解決上述所提及之限制，我們提出了一個人機介面系統嘗試去改善重症患者之生活，與此同時也著眼於此系統作用於一般使用者的可行性。 此研究根據眼電位法(Electrooculography, EOG)為理論基礎，達成高準確率的眼動偵測，進而應用於人機介面系統。本研究主要成果有三: (1) 高準確率的眼動行為偵測，其包含了眼睛的掃視、凝視以及眨眼。其中在掃視偵測當中提供了多達十種不同方向，不同視角的狀態辨識。(2)結合乾式電極，提供使用者更方便、更舒適的使用介面。(3)基於眼動偵測，設計出一套眼動撥號系統。驗證了眼電位法在人機介面上的可行性與可靠性。

In assistive research area, human-computer interface (HCI) technology is used to help disable people by conveying their intention and thinking to the outside world. Many HCI systems based on eye movement have been proposed to assistive disable people. However, due to the complexity of algorithm and difficulty of hardware implementation, there are rare general purpose designs considering the practicality and stability in real-life. Therefore, to solve these limitations and problems, a HCI system based on electrooculography (EOG) is proposed in this study. The proposed classification algorithm provides the eye state detection including fixation, saccade and blink. Moreover, in saccade detection, this algorithm can distinguish ten kind of saccade movements (i.e., up, down, left, right, much left, much right, up-left, down-left, up-right and down-right). In addition, we development a HCI system based on eye movement classification algorithm. This system provides an eye-dialing interface that can be facilitated to improve the life of disable people. The significant results are achieved that proved the performance of the proposed classification algorithm. Moreover, the EOG-based system, which can detect ten different eye movement features, is potential to be performed in real-life applications.