Eye Tracker for the Disabled

Eye Tracking Software

Hi, my name is Lucas Ahn, otherwise known as Soo Young Ahn. I am currently enrolled in Asia Pacific International School, and this is my project!

Step 1: Background Information

Paper: "Accurate Eye Centre Localisation by means of Gradients" by Fabian Timm and Erhardt Barth

- The estimation of the eye centers is used in several computer vision applications such as face recognition or eye tracking

- EYE CENTRE LOCALISATION

Math Theory

Step 2: Main Principle

Evaluation of (1) for an exemplary pupil with the detected centre marked in white (left). The objective function achieves a strong maximum at the centre of the pupil; 2-dimensional plot (centre) and 3-dimensional plot (right)

Step 3: Webcam Gaze Tracker

https://github.com/iitmcvg/eye-gaze

Step 4: Webcam Based Eye Tracking Pros and Cons

Pros: Cheap, available for almost everyone, fast turnaround and available at anywhere with a webcam

Cons: Less accurate, Steady posture, Low light condition, Low frame resolution

Step 5: Open CV: Eye Detection

https://www.usability.gov/how-to-and-tools/methods/personas.html

Step 6: Eye Tracker for Disabled Project

Eye detection --> Mouse control --> Web browsing

Results:

Step 7: Upgraded Project for Mobile

ARKit for iOS + Cocoapods Library

Step 8: Eye Tracking Functions

Up, Down, Right, Left Recognition

Step 9: Eye Track Browser Development Process

iOS + ARKit + Cocoapods

(OpenCV Library) Language : Swift + Objective C

Step 10:

Step 11: Reason Why I Made This Browser

This browser was created for the purpose of helping disabled people browse on the internet for several purposes such as searching for jobs online or simply for entertainment.