Eye Movement Driven Cursor Control Using Computer Vision Technique

Abstract: In the field of human-computer interaction, eye tracking technology has drawn a lot of attention, especially for helping people with physical disabilities who can't use conventional input devices like a mouse or keyboard. The creation of an inexpensive eye-controlled mouse system that allows users to manipulate the movement of a computer cursor by blinking and eye gaze is presented in this paper. Using a standard webcam, the proposed system tracks eye movements in real time and detects facial landmarks using computer vision and deep learning techniques. Eye positions are determined using image processing techniques, and cursor control is achieved by mapping gaze direction to screen coordinates. Click operations are carried out by blink detection, enabling users to engage with applications without making physical contact. Python is used to implement the system, and libraries like OpenCV, MediaPipe, and PyAutoGUI are used for cursor automation, video processing, and facial landmark detection. The suggested method can provide precise cursor movement and dependable click detection under typical lighting conditions, according to experimental results. For users with mobility impairments, the developed system provides an accessible and reasonably priced assistive technology solution that improves computer accessibility and hands-free interaction.