A robust recognition approach in eye-based dwell-free typing

Alternative form of text entry is a tremendous benefit for a subset of physically challenged people, spurning the development of many assistive technologies. However, speed of text entry with these methods is still a critical problem. Eye gaze technologies have potential for text entry, but still tend to relatively slow. Recently dwell-free eye-typing systems have been proposed, but can be vulnerable to some common text entry problems, such as selection of the wrong character. In this paper, we propose a recognition approach for inferring the words which the user intends to type. The method is robust to missing letters and even when a neighboring character on the keyboard is incorrectly selected. Simulation and experiments results suggest that our proposed approach has better accuracy and more resilience to text entry errors than currently proposed dwell-free systems.