「眼寫（Eye writing）」是本團隊所發明的一種新的溝通方法，靠偵測使用者眼球移動的特定軌跡，來辨識其所欲表達的符號。此系統可以應用於一個意識清醒卻無法正常說話或用手寫字的漸凍症（A.L.S.）、運動神經元疾病（M.N.D.）或中風等疾病患者身上。本研究以眼電圖法 （Electro-OculoGraphy, EOG）來擷取眼睛移動的軌跡，藉由量測眼睛周圍皮膚微弱的電位差，以得知眼睛移動的方向。系統將EOG訊號擷取後，經由數位訊號處理來濾除雜訊，利用串音規則策略來判斷眼動軌跡路徑，辨識出使用者所要表達的符號。系統裡共建構了60個符號，包含注音符號37個、五聲符號5個、阿拉伯數字0~9共10個符號、3個標點符號以及5個控制符號。經過8個志願者的測試，証明了本系統的可行性，並且其辨識率高達90%以上。這樣的辨識率加上本系統提供的字句編輯和語音合成功能，足以取代口語及手寫的表達方式，讓漸凍人只靠眼球轉動便能與他人溝通。本系統未來的發展，首先將擴增新符號，例如漢字、英文字母和英文單字等；另一方面，為了提高漸凍症患者的自主性以及降低其受照顧的需求，將進一步利用此眼寫方法來控制其日常生活中所需使用的設備，例如電腦、電視、電話、輪椅等。希望奠基於本眼寫方法所發展出來的一系列輔具技術，不只能降低社會和家庭照顧漸凍症一類病患的成本和心力，更有意義的是為病患帶來比以往更便利和舒適，而且更有尊嚴的生活。 Eye-writing herein introduced is a novel language communication method wherein the eyes fill the role of a writing organ. This technology will be especially useful for severe amyotrophic lateral sclerosis (ALS) patients who have lost oral speaking and hand-writing abilities. An eye-writing system for Mandarin Phonetic Symbols detects the traces of eye movements and determines their corresponding symbols by pattern recognition. In this study, we measured the eye movements by electro-oculograophy (EOG). The electrical potential difference measured between the skins above and below the eyes reflected the eye movement in the vertical direction. That measured between the skins to the left and to the right of the eyes reflected the eye movement in the horizontal direction. We evaluated the eye-writing system with a symbol set consisting of 37 Mandarin phonetic symbols, 5 lexical-tone symbols, 10 Arabic numeral symbols, 3 punctuation marks, and 5 control symbols. The symbol set is expandable to contain new symbols. Experiments on 8 voluntary human subjects showed recognition rate is higher than 90%. Based on the result we got in the feasibility study, we envision that the system is capable of controlling computers, televisions, or wheelchairs by incorporating some control algorithms.
