EyeBoard: A fast and accurate eye gaze-based text entry system

摘要

Over the last three decades, eye gaze has become an important modality of text entry in large and small display digital devices covering people with disabilities beside the able-bodied. Despite of many tools being developed, issues like dwell time optimization, visual search time and interface area minimization, eye-controlled mouse movement stability etc. are still points of concern in making any gaze typing interface more user friendly, accurate and robust. In this paper, we propose EyeBoard, an gaze-based text entry system which optimizes the constituent virtual keyboard layout with respect to eye gaze movement as well as adjusts dwell time dynamically in accordance with user comfort level. Performance evaluation shows that proposed interface achieves on an average 14% higher text entry rate over the existing interfaces. As designed, the proposed interface can effortlessly be suited in small display devices like Mobile phone, PDA etc. Although the experiments have been conducted with able-bodied users, those can easily be replicated for people having severe motor disabilities.