An app that uses the phone's cameras to watch people read and identify signs of dyslexia based on their eye movements.
Early detection of dyslexia in children (and adults).
Load the app and place the phone under the book or a piece of paper, so that the camera is sticking out (as shown in the header image). The phone's camera(s) should see the reader's face.
Print the same piece of text, load the app on your phone, and have it watch your child reading.
Although dyslexia is due to differences in the brain, no blood tests or lab screenings can detect it. Instead, careful evaluation (testing) of common signs identifies someone with this reading problem.
Dyslexia is a brain-based type of learning disability that specifically impairs a person's ability to read. No blood tests or lab screenings can detect it. These people typically read at levels significantly lower than expected despite having normal intelligence. The disorder varies from person to person. There are some common characteristics such as difficulty with reading, the manipulation of sounds, spelling, and/or rapid visual-verbal responding.
Training the neural network
The proposed app's software is powered by a neural network. Train it on thousands of people that read the same piece of text. A few thousand people without dyslexia and a few thousand with. Based on the eye movement patterns the software learns to recognize the difference. Provide the network with enough training examples and it could learn to distinguish between different types of dyslexia.
Not only the eyes, but also facial expressions, squinting, frowning, etc. are taken into consideration. Let the neural network find common patterns.
Darko Savic Feb 13, 2022