Gaze-Based Text Entry Systems

Text input is a common task in interaction research. The alternative text production systems are typically tested by usability studies and also by standardized performance measurements like word-per-minute, Error Rates etc. Text entry by eye gaze is quite similar to any screen-based text entry technique, such as the on-screen keyboards. The interface is more or less the same, only the interaction technique of pointing and selecting changes as eye gaze is used instead of a stylus or other pointing devices. However, this change in the interaction technique brings a number of design issues that make text entry by eye gaze a unique technique with its own set of research problems.

The procedure of typing by eye gaze is that the user focuses on the desired letter by looking at one of the keys on the on-screen keyboard. Then, the system gives feedback on the focused item like by highlighting the focused item or by moving a “gaze cursor” over the focused key. The focused item can be selected by using, for instance, a separate switch, a blink, a wink, or even a wrinkle or any other (facial) muscle activity. Muscle activity is typically measured by electromyography. Practically, blinks and winks can also be detected from the same video signal used to analyze eye movements. For severely disabled people, dwell time is the best and often the only way of selection.

Layouts with large keys are still required and used in today’s systems. Even though the state-of-the-art eye trackers are fairly accurate, the so-called “low-cost systems” still do not reach the accuracy required for a QWERTY keyboard.

While typing, after tapping a character, user has to visually search the next intended character to be typed on the interface. The minimization of the visual search time directly affects the text entry rate. For the eye gaze based typing task, there is a trade-off between how fast typing can be performed and how many mistakes are made in performing the task. That is, a user can either type the characters very fast with a large number of errors or very slow with very few errors. When asked to perform quick typing as well as possible, people will apply various strategies that may optimize speed, optimize accuracy, or combine the two. For this reason, the interface design strategy should include the minimization of speed accuracy trade-off. So, in context of eye gaze based text typing interface development, speed accuracy trade-off must be addressed.

Eye gaze based typing can be more fast and easier than “normal mouse click” based typing as it is proved that eye movement are much faster than hand. Thus gaze is not as accurate as input device as desktop mouse, but it can be much faster at pointing because of the speed of the eye.

Work concluded:

  • Virtual keyboard layout optimization with respect to size of the key, space between keys and zoom of the layout.
  • Re-arrangement of alphabet keys for efficient text entry rate as well as easy learning.
  • Proposed dynamically adapting the dwell time of the interface based on the typing efficiency of the users.
  • Language independent design development so that it can also work for more complex languages like Hindi and Chinese.
  • Addition of different functionality to the design for enhancing the results.
  • Proposed alternate and more accurate method for dwell time.