Gaze Tracking Using Difference Image Entropy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing input interfaces for mobile and electronic devices, such as keypads and mice, are not conducive to intuitive drawing, writing, or menu selection, and there is a need for a method that allows users to perform these tasks without traditional input methods.
Innovation Solution
A gaze tracking apparatus and method using difference image entropy, which detects the user's eye region, computes entropy values between the eye region and reference images, and recognizes the user's gazing direction to enable input control and menu selection without traditional interfaces.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If traditional input interfaces (keypad, mouse) are used, then device operation is reliable, but ease of operation and intuitiveness deteriorate
Solution Approach 1:
The patent replaces traditional mechanical input interfaces (keypad, mouse) with a gaze-based optical input system. The camera captures eye images, and the system determines gazing direction through image processing and coordinate transformation, substituting physical interaction with optical detection and computational analysis.
2Ease of operation
If gaze tracking is implemented without traditional interfaces, then ease of operation improves, but measurement precision and detection accuracy worsen
Solution Approach 1:
The patent introduces an intermediary coordinate transformation process that maps camera coordinates to display coordinates through calibration. This intermediary step accounts for the geometric relationship between the camera, user's eye, and display screen, improving the precision of gazing direction detection.
Solution Approach 2:
The system performs calibration by detecting known reference points on the display screen and using this information to establish accurate coordinate transformations. This feedback mechanism allows the system to learn and compensate for individual user characteristics, enhancing measurement precision.
3Measurement precision
If multiple reference images are compared to determine gazing direction, then measurement precision improves, but computing time and processing complexity worsen
Solution Approach 1:
The patent pre-divides the display screen into multiple regions and pre-generates reference images for each region before actual gaze tracking begins. This preliminary preparation allows the system to quickly compare the current eye image against pre-existing references, reducing real-time processing time while maintaining accuracy.
Data Source
AI summary
In accordance with one aspect of the present invention, there is provided a gaze tracking apparatus using difference image entropy, comprising: image detection module for detecting user's eye region image from image of the user taken by picture-taking apparatus which is connected to the gaze tracking apparatus; image selection module for computing entropy value of difference image between the eye region image and a plurality of reference images respectively indicating each gazing direction and selecting reference image with least difference image entropy value among the plurality of reference images; and gaze tracking module for recognizing user's gazing direction by regarding gazing direction that the selected reference image indicates as user's gazing direction.