Year: 2025
Type: article
Abstract: Eye gaze detection is becoming an essential component in modern Human–Computer Interaction (HCI) due to its applications in assistive systems, driver monitoring, educational technologies, and immersive environments like VR/AR. Traditional gaze-tracking relies heavily on infrared sensors or specialized hardware, making such systems expensive and inaccessible for wide-scale deployment. This paper introduces GazeTrack, a real-time, lightweight, and cost-effective deep learning-based gaze detection system that operates solely using a standard webcam. By combining MediaPipe Face Mesh for extracting 468 facial landmarks with geometric analysis of the eye region, the system accurately classifies gaze directions such as Left, Right, Up, Down, and Center. The system maintains high accuracy (above 90%) and real-time performance (30–60 FPS) on standard hardware, making it highly suitable for low-cost real-world applications.
Authors: Dhanushree C P, Nisarga N P, Manoj Kumar C S, Niba Mehak, Abdul Rahman
Language: English
Subfield: Human-Computer Interaction
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
OpenAlex ID: W4417216714
FWCI:
Cites:
Cited by:
Related to: