Chinese character input method applicable to gaze input

Abstract

The invention discloses a Chinese character input method applicable to gaze input, which includes the steps: generating a candidate character area and a to-be-inputted next character code area according to currently gazed character codes of a user by utilizing stroke input as an input mode; if one character expected to be inputted by the user appears in the candidate character area, leading the user to gaze the character, and inputting the character after a setting time so that the input is completed; otherwise, leading the user to gaze a next character code needing to be inputted, and taking the character code which is currently gazed by the user as a center, wherein the next possibly inputted character code and the next possibly inputted candidate character are popped out from the left side and the right side; and completing user input. Usability and input efficiency of the gaze-based character input mode are improved.

Description

Technical field [0001] The invention belongs to the field of gaze tracking applications and text input, and relates to a solution for gaze application analysis and text input. Background technique [0002] Vision-based human-computer interaction is a hot issue in the current image processing field. Its basic principle is to determine the user's gaze direction based on the characteristics and position of the eyes and other facial cues, as an optional or complementary computer The input channel provides a new way for human-computer interaction. As gaze tracking technology matures, the current time and space accuracy achieved by eye tracking makes it possible to replace traditional pointing devices with gaze tracking technology and become a brand new input channel. [0003] The existing text input based on gaze tracking is similar to using the virtual keyboard on the computer screen to input. The interface is basically the same, except that the actions of indicating and triggering th...

AI Technical Summary

Problems solved by technology

[0005] There are three main problems in inputting with the sight line: first, there is an unconscious saccade in the human line of sight, that is, when the user looks at a certain point, the point of fixation does not fall on the point stably, but in a centered point. Random jumps in a small range

The line-of-sight input method is a continuous process, unlike the traditional hand-knocking keyboard, which is a series of discrete inputs, the line-of-sight input is a track, and it is difficult for us to judge the actual intention of the user from the track. characters

For example: using the pinyin input method to input the Chinese character "I", the traditional keyboard input method requires the user to tap the buttons "w" and "o" in sequence to complete the input, but when using the line of sight input method, the user looks at the buttons on the computer screen in turn. For the "w" and "o" characters of the virtual keyboard, the gaze point will inevitably pass through the characters between "w" and "o", which will cause ambiguity in the input information

The third problem is the start and end of input, that is, similarly, the input of sight is a continuous process, how to judge when the user starts to input, when to end the input, and whether it is meaningless input, such as the user is staring at the screen in a daze, etc.

ShapeWriter solves the problem of inputting discrete characters in a continuous process by continuously sliding over the characters to be input. However, ShapeWriter is only suitable for English input, and it still does not solve the problem of judging the start and end of input.

Images