Eye Gaze Detection Using Standard Camera and Image Processing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current eye-tracking systems for individuals with ALS are expensive, not robust under various light conditions, require frequent recalibration, and have immobile setups, making them impractical for portable use.
Innovation Solution
A portable eye gesture communication system using a camera, database, and processor to detect and interpret eye gaze directions, allowing single-eye gestures for character entry and accounting for different lighting conditions, integrated into mobile devices for ease of use.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If high-tech eye gaze tracking systems are used, then measurement precision is improved, but device complexity and cost increase
Solution Approach 1:
The patent uses a standard camera to capture images of the user's eyes and creates a digital model/copies of the eye structure. By analyzing the position of reflective highlights (specular reflections) in these copied visual representations, the system determines gaze direction without requiring specialized eye-tracking hardware. This copying approach maintains measurement precision while dramatically reducing device complexity.
Solution Approach 2:
The patent replaces complex mechanical/optical eye-tracking systems with a software-based image processing approach using a standard camera. Instead of using specialized infrared cameras, head-mounted trackers, or other sophisticated hardware, the system substitutes these mechanical systems with computational analysis of regular camera images, thereby reducing device complexity while maintaining functionality.
2Measurement precision
If specialized eye tracking hardware is used, then measurement precision is improved, but loss of substance increases
Solution Approach 1:
The patent employs inexpensive, widely available standard cameras (such as those in smartphones or webcams) instead of costly specialized eye-tracking hardware. These cheap camera devices can be easily replaced or upgraded, and their low cost dramatically reduces the overall system expense while still providing sufficient measurement precision for gaze-based communication.
3Device complexity
If traditional E-tran boards are used, then device complexity is reduced, but productivity decreases
Solution Approach 1:
The system incorporates automated image processing and gaze direction calculation algorithms that automatically analyze captured eye images and determine gaze position without requiring manual intervention or complex setup by communication partners. The system self-calibrates by tracking eye movements and automatically maps gaze directions to keyboard positions, thereby maintaining simplicity while significantly improving communication productivity compared to manual E-tran board methods.
4Measurement precision
If eye tracker calibration is performed before each use, then measurement precision is improved, but loss of time increases
Solution Approach 1:
The system performs calibration actions in advance by capturing a set of reference eye images during an initial setup phase. These pre-captured images establish the relationship between eye position and gaze direction for that specific user. By completing the calibration process beforehand, the system eliminates the need for time-consuming recalibration before each communication session, thereby reducing time loss while maintaining measurement precision through the stored calibration data.
Data Source
AI summary
Techniques for text entry using gestures are disclosed. As disclosed, a camera may capture a frame and the face of the user can be detected therein. Landmarks can be aligned to the face in the captured frame. A left eye image and a right eye image may be extracted from the captured frame. The left eye image and the right image each may be resized and compared to a calibration template. A direction of eye gaze may be determined based upon the comparison. A character or word may be predicted based upon the determination of the direction of eye gaze and a known configuration of an eye gaze board (e.g., an E-tran board). The predicted character or word can be included as a part of a text-based message.