An Eye-Tracking System based on Inner Corner-Pupil Center Vector and Deep Neural Network

Area of Science:

• Computer Vision
• Human-Computer Interaction
• Biomedical Engineering

Background:

• Eye tracking is crucial for understanding visual behavior and emotional states.
• Current eye trackers are often expensive and require head stabilization.
• Applications span psychology, medicine, education, and virtual reality.

Purpose of the Study:

• To develop a cost-effective and head-motion-tolerant eye-tracking system.
• To improve accessibility and usability of eye-tracking technology.
• To compare the proposed system's performance against existing algorithms.

Main Methods:

• Development of an inner corner-pupil center vector (ICPCV) based eye-tracking system.
• Utilizing a deep neural network for gaze estimation.
• Comparative performance analysis with other state-of-the-art eye-tracking algorithms.

Main Results:

• The proposed ICPCV system achieves accurate gaze estimation.
• The system operates effectively without requiring head immobilization.
• Performance evaluation demonstrates superiority over existing eye-tracking methods.

Conclusions:

• The ICPCV system offers a viable, affordable alternative to expensive eye trackers.
• This technology enhances the practicality of eye tracking in diverse applications.
• Further research can explore its integration into real-world scenarios.