18644889. SYSTEMS AND METHODS OF CAPTURING EYE-GAZE DATA simplified abstract (Microsoft Technology Licensing, LLC)
Contents
SYSTEMS AND METHODS OF CAPTURING EYE-GAZE DATA
Organization Name
Microsoft Technology Licensing, LLC
Inventor(s)
Jatin Sharma of Sammamish WA (US)
Jonathan T. Campbell of Redmond WA (US)
Jay C. Beavers of Duvall WA (US)
Peter John Ansell of Renton WA (US)
SYSTEMS AND METHODS OF CAPTURING EYE-GAZE DATA - A simplified explanation of the abstract
This abstract first appeared for US patent application 18644889 titled 'SYSTEMS AND METHODS OF CAPTURING EYE-GAZE DATA
Simplified Explanation: The patent application describes a system for collecting eye-gaze data to train an eye-gaze prediction model by moving a symbol along a scan path on a grid screen and capturing facial images at eye-gaze points.
Key Features and Innovation:
- Selecting a scan path through regions of a grid screen
- Moving a symbol as an eye-gaze target along the scan path
- Receiving facial images at eye-gaze points
- Uniform distribution of eye-gaze points within regions
- Smaller regions near screen edges and corners
- Shifting centers of regions towards edges for higher data density
- Capturing more eye-gaze points near edges and corners
- Interactive enhancement of facial image variations
Potential Applications: This technology could be used in eye-tracking systems for various applications such as human-computer interaction, market research, and assistive technologies for individuals with disabilities.
Problems Solved: The technology addresses the need for accurate eye-gaze prediction models by collecting data efficiently and enhancing facial image variations for improved training.
Benefits:
- Enhanced accuracy in eye-gaze prediction
- Efficient data collection process
- Improved training of eye-gaze prediction models
Commercial Applications: The technology could be applied in industries such as gaming, advertising, healthcare, and education for developing interactive systems and personalized user experiences.
Prior Art: Prior research in eye-tracking technology and facial recognition systems could provide insights into similar approaches to collecting eye-gaze data and enhancing facial images for training models.
Frequently Updated Research: Stay updated on advancements in eye-tracking technology, facial recognition algorithms, and machine learning techniques for eye-gaze prediction models.
Questions about Eye-Gaze Data Collection: 1. How does the system ensure uniform distribution of eye-gaze points within regions? 2. What are the potential challenges in capturing accurate eye-gaze data near screen edges and corners?
Original Abstract Submitted
Systems and methods are provided for collecting eye-gaze data for training an eye-gaze prediction model. The collecting includes selecting a scan path passing through a series of regions of a grid on a screen of a computing device, moving a symbol as an eye-gaze target along the scan path, and receiving facial images at eye-gaze points. The eye-gaze points are uniformly distributed within the respective regions. Areas of the regions that are adjacent to edges and corners of the screen are smaller than other regions. The difference in areas shifts centers of the regions toward the edges, density of data closer to the edges. The scan path passes through locations in proximity to the edges and corners of the screen for capturing more eye-gaze points in the proximity. The methods interactively enhance variations of facial images by displaying instructions to the user to make specific actions associated with the face.
