How Eye Trackers Detect Eyelid Movements and Blinks

This patent describes a method for eye tracking systems to precisely detect eyelid movements and blinks by comparing a current eye image to a reference image, then analyzing the differences in rows of pixels.

What it covers

This eye tracking system works by taking two pictures of a user's eye: a 'reference image' and a 'current image' (Claim 1). It then finds the differences between these two images, creating a 'differential image' where only what has changed is visible. This differential image is like a grid of pixels, each showing how much it changed (Claim 1). The system then adds up or combines the change values in each horizontal row of pixels to get 'row values' (Claim 1, Claim 6). Finally, it uses these row values to figure out 'eyelid data,' such as the exact position of an eyelid edge (Claim 7) or whether the eye is blinking (Claim 9). For example, if you blink, the system would see a big change in certain rows of the differential image, indicating a blink.

What it doesn't cover

• —Does not cover eye tracking systems that detect eyelid movement without first creating a differential image by comparing a current image to a reference image.
• —Does not cover systems that determine eyelid data solely from analyzing individual pixels or columns, rather than combining differential intensity values in corresponding rows (Claim 1).
• —Does not cover eye tracking methods that rely only on infrared reflections or pupil dilation without image differencing for eyelid detection.
• —Does not cover systems that track the entire eye's movement without specifically processing images to extract eyelid location or blink data.
• —Does not cover methods for determining eyelid data that do not involve a two-dimensional pixel array with differential intensity values.

The clever bit

The clever part is using a 'differential image' created by subtracting a reference image from a current one, then combining pixel intensity differences specifically along rows. This highlights only the eyelid movement, making it easier and potentially faster to detect changes like blinks or eyelid position without needing complex analysis of the entire eye image.

Why it matters

Accurate eyelid tracking is crucial for many applications, from understanding user attention in virtual reality to diagnosing neurological conditions. By precisely identifying eyelid positions and blinks, this technology can improve the reliability of eye-tracking data, making it more useful for both research and commercial products. This precision helps prevent false readings and provides richer information about a user's state.

Real-world examples

• 1.Virtual reality headsets with eye tracking
• 2.Augmented reality glasses
• 3.Driver monitoring systems in cars
• 4.Assistive technologies for people with disabilities
• 5.Gaming peripherals with eye control
• 6.Market research tools for attention analysis
• 7.Clinical diagnostic tools for eye conditions