This project aims to detect faces and calculate Gaze Points.
Gaze points are the fundamental units of measurement utilized in eye tracking research.
Each gaze point represents an individual record of a participant's gaze at a specific moment.
The number of these individual moments per second depends on the sampling rate of the eye tracking device.
I employed CameraX to initiate a camera preview. Additionally, I utilized ML-kit for detecting faces and their landmarks. The process begins immediately with face detection. When a face is detected, the system attempts to obtain eye landmarks for both eyes. If these landmarks are available, it proceeds to calculate the gaze point.
- Best-case scenario: When it successfully detects a face and both eyes.
- When no face is detected.
- When a face is detected, but the landmarks for the eyes are not clear.
- When there is more than one face detected.
https://drive.google.com/file/d/1gXo4yceQTww4hI5zgYV7oBvWIEw0lSWn/view?usp=sharing
This project is licensed under the MIT License - see the LICENSE.md file for details.
If you have any questions, feedback, or inquiries, please don't hesitate to get in touch with me. I'm here to assist you!
Linkedin: www.linkedin.com/in/Tareq-ghassan
Feel free to use the contact details provided above, and I'll respond as soon as possible. Your input is valuable to me, and I look forward to hearing from you.
