IJIREEICE ISSN (O) 2321-2004, ISSN (P) 2321-5526

International Journal of Innovative Research in Electrical, Electronics, Instrumentation and Control Engineering
Impact Factor 8.021Peer-reviewed & Refereed journalVol. 12, Issue 5, May 2024
DOI: 10.17148/IJIREEICE.2024.12520

EYE GAZE TRACKING TO CONTROL

CURSOR MOVEMENT
Prof.Vinutha.N1, Anusha.N2, Anusha.P3, Punyashree.C4,Vishwas .RP5
Faculty, Department of Computer Science and Engineering, Vidya Vikas Institute of Engineering and Technology,
Mysore, Karnataka1
Students, Department of Computer Science and Engineering, Vidya Vikas Institute of Engineering and Technology,
Mysore, Karnataka2-5

Abstract: Controlling a mouse can be particularly challenging for individuals with physical disabilities. To address this
issue, we propose a system that enables mouse cursor control using eye movements. Eye gaze offers an alternative method
for computer access, allowing users to control the mouse by simply moving their eyes. This approach is especially
valuable for those who find touchscreens and traditional mice inaccessible. Eye movement serves as a crucial real-time
input medium for human-computer interaction, particularly for individuals with physical disabilities. To enhance the
reliability, mobility, and usability of eye tracking technology in user-computer interactions, we have developed a novel
eye control system that utilizes a standard webcam, eliminating the need for additional hardware.

Our proposed system focuses on providing a simple and convenient interactive mode that relies solely on the user's eye
movements. The system's usage flow is designed to align seamlessly with natural human behaviours. The implementation
includes tracking both the iris and cursor movement based on the iris position, allowing for precise control of the cursor
on the screen. This eye control system is implemented using Python and leverages webcam technology to detect and
interpret eye movements. The simplicity and accessibility of this system make it a promising solution for enhancing
computer usability for physically challenged individuals.

I. INTROUDCTION

The increasing demand for intuitive and immersive human-computer interaction has spurred the development of novel
input methods. Traditional mouse-based interaction may not always be feasible or convenient, especially in virtual reality
environments or for individuals with physical impairments. To address these challenges, researchers have explored the
use of machine learning techniques to develop human-controlled virtual mouse systems. These systems aim to interpret
human gestures and translate them into corresponding mouse commands, enabling users to interact with digital interfaces
in a more natural and flexible manner.

Eye-controlled virtual mouse technology offers users the ability to interact with their computers using only their eyes.
This technology is particularly beneficial for individuals with physical disabilities or motor impairments that make
traditional computer input methods difficult or impossible. The system employs an eye tracker to detect the movements
of the user's eyes, which are then translated into mouse movements. This allows the user to move the mouse pointer and
click on items on the screen simply by looking at them.

The implementation of this technology can significantly enhance the quality of life for individuals with disabilities,
enabling them to interact with computers in ways that were previously inaccessible. Eye-controlled virtual mouse systems
not only promote greater accessibility but also pave the way for more inclusive and user-friendly digital environments.

II. LITERATURE SURVEY

1. Eye-Controlled Mouse Cursor for Physically Disabled Individuals

Authors: Mohamed Nasor, Mujeeb Rahman K K, Maryam Mohamed, Haya Ansari, Farida Mohamed (2018)
This paper presents a new algorithm for controlling a computer screen cursor using eye movements. By accurately
detecting the position of the iris, the algorithm maps this to a specific position on the screen, enabling physically disabled
individuals to control the cursor's movements (left, right, up, down) and perform actions like opening and closing files or
applications through a clicking mechanism.

© IJIREEICE This work is licensed under a Creative Commons Attribution 4.0 International License 121
 IJIREEICE ISSN (O) 2321-2004, ISSN (P) 2321-5526

International Journal of Innovative Research in Electrical, Electronics, Instrumentation and Control Engineering
Impact Factor 8.021Peer-reviewed & Refereed journalVol. 12, Issue 5, May 2024
DOI: 10.17148/IJIREEICE.2024.12520
2. Mouse Cursor Control with Eye Movement Using OpenCV and Machine Learning
Authors: Murali Manoharan, Jaya Krishna Alagappan Pachamuthu, Surya Ganapathy (2024)
For people with physical challenges, using a mouse can be very difficult. Our proposed solution uses eye movements to
control the mouse. Eye gaze is a method where users control their computer with their eye movements, especially helpful
for those who can't use touchscreens or traditional mice. This system uses a webcam and machine learning to improve
the reliability, mobility, and usability of eye tracking for user-computer interaction, allowing users to control the cursor
with just their eyes.

3. System Cursor Control Using Human Eyeball Movement

Authors: Dhanasekar J, Guru Aravindh K B, Kiren A S, Faizal Ahamath A (2024)
This paper develops a hands-free system for controlling a computer cursor using eyeball movements. Using image
processing and machine learning algorithms in Python, the system translates eyeball movements and blinks into cursor
movements and clicks. This system is accurate and user-friendly, improving computer accessibility for individuals with
motor impairments. It has potential applications in gaming and virtual reality.

4. Human-Eye Controlled Virtual Mouse

Authors: Mr. Dhanaraju, Dr. Sreenivas Mekala, A. Harsha Vardhan Rao, CH. Pavan Kumar, R. Lokesh (2024)
In the digital era, hands-free computing is essential for individuals with disabilities, like quadriplegics. This paper
introduces a Human-Computer Interaction system that uses eye movements (blinking, staring, squinting) to control the
mouse cursor. The system is implemented using Python, OpenCV, NumPy, and basic camera technology, making it
completely hands-free without requiring additional hardware or sensors.

5. Eyeball Movement-Based Cursor Using Deep Learning

Authors: Shubham Rane, Nihal Salian, Mohit Shetty, Rohan Shinde, Swati Rane (2021)
This paper proposes a hands-free human-machine interaction system for better communication between humans and
computers. Long hours of using a mouse can lead to wrist and hand issues. This system, designed for differently-abled
people, allows them to control the mouse with their eyes. Using deep learning and machine learning, the system accurately
tracks eye movements to control the cursor. The system includes noise reduction filters to ensure smooth and accurate
operation.

III. METHODOLOGY

PROPOSED METHODOLOGY
1. System Design
Develop a system to control the mouse cursor using eye movements for physically challenged individuals.
Approach: Utilize a webcam to track eye movements and implement the system using Python without additional
hardware.

2. Hardware and Software Requirements

Hardware: Standard webcam
Software: Python, OpenCV for image processing, machine learning libraries for eye movement detection

3. Eye Movement Detection

Webcam Setup: Configure the webcam to capture real-time video of the user's eyes.
Image Processing: Use OpenCV to preprocess the video frames, enhancing the visibility of the iris.
Iris Detection: Implement algorithms to accurately detect the position of the iris within each frame.

4. Mapping Eye Movements to Cursor Movements

Coordinate Mapping: Develop a mapping mechanism to translate iris position to corresponding cursor movements on the
screen.

Calibration: Implement a calibration step to align the detected iris position with specific screen coordinates.

5. Cursor Control Mechanism

Movement Control: Allow the cursor to move in response to the detected direction of the user's gaze (left, right, up,
down).

Clicking Mechanism: Implement a method to simulate mouse clicks through prolonged eye focus or blinking.

© IJIREEICE This work is licensed under a Creative Commons Attribution 4.0 International License 122
 IJIREEICE ISSN (O) 2321-2004, ISSN (P) 2321-5526

International Journal of Innovative Research in Electrical, Electronics, Instrumentation and Control Engineering
Impact Factor 8.021Peer-reviewed & Refereed journalVol. 12, Issue 5, May 2024
DOI: 10.17148/IJIREEICE.2024.12520
6. User Interface Design
Interactive Mode: Design the system to follow natural human habits, ensuring intuitive and seamless interaction.

7. Implementation
Programming: Develop the system using Python, integrating OpenCV for image processing and machine learning
techniques for accurate eye tracking.

IV. RESULTS & DISCUSSION

➢ Effectiveness for Physically Challenged Users

The eye-controlled mouse cursor system significantly improved accessibility for users with physical disabilities, allowing
them to interact with computers without using their hands.
The system's reliance on eye movements provided a reliable alternative to traditional input devices, enhancing the
autonomy and independence of users.

➢ Challenges and Limitations

While the system performed well under controlled conditions, varying ambient light and background conditions affected
the accuracy of iris detection.

© IJIREEICE This work is licensed under a Creative Commons Attribution 4.0 International License 123
 IJIREEICE ISSN (O) 2321-2004, ISSN (P) 2321-5526

International Journal of Innovative Research in Electrical, Electronics, Instrumentation and Control Engineering
Impact Factor 8.021Peer-reviewed & Refereed journalVol. 12, Issue 5, May 2024
DOI: 10.17148/IJIREEICE.2024.12520
Some users with severe eye movement restrictions or conditions such as nystagmus experienced difficulty in achieving
consistent cursor control.

Prolonged use of the system could lead to eye strain, indicating a need for further optimization in terms of user comfort
and ergonomics.

➢ Comparison with Existing Technologies

Compared to other assistive technologies like head-tracking or voice-controlled systems, the eye-controlled cursor system
offered a more direct and natural method of interaction.

The system's reliance on a standard webcam without additional hardware reduced costs and complexity, making it more
accessible and easier to deploy.

➢ Future Improvements
Enhancing the robustness of the system to cope with varying environmental conditions would improve overall reliability.
Integrating machine learning models that adapt to individual user patterns could further increase the accuracy and usability
of the system.

Exploring additional features such as multi-click options, scroll functions, and customizable gestures would expand the
system's functionality.

➢ Implications for Broader Applications

Beyond assisting physically challenged individuals, the eye-controlled mouse cursor system has potential applications in
fields such as virtual reality, gaming, and hands-free control environments.

Its ability to provide an alternative interaction method could lead to innovations in how users interact with digital
interfaces, promoting more inclusive and versatile technology use.

V. CONCLUSION

The development of an eye-controlled mouse cursor system represents a significant advancement in assistive technology,
providing a viable solution for individuals with physical disabilities who find traditional input methods challenging. This
project successfully demonstrates that eye movements can be harnessed to control computer cursors, offering an intuitive
and accessible alternative to the conventional mouse.

REFERENCES

[1]. Q. Sun, J. Xia, N. Nadarajah, T. Falkmer, J. Foster, and H. Lee, “Assessing drivers’ visual-motor coordination using
eye tracking, GNSS and GIS: a spatial turn in driving psychology,” Journal of Spatial Science, vol. 61, no. 2, pp.
299–316, 2016.
[2]. N. Scott, C. Green, and S. Fairley, “Investigation of the use of eye tracking to examine tourism advertising
effectiveness,” Current Issues in Tourism, vol. 19, no. 7, pp. 634–642, 2016.
[3]. K. Takemura, K. Takahashi, J. Takamatsu, and T. Ogasawara, “Estimating 3-D point-of-regard in a real environment
using a head-mounted eye-tracking system,” IEEE Transactions on Human-Machine Systems, vol. 44, no. 4, pp.
531–536, 2014.
[4]. R. J. K. Jacob and K. S. Karn, “Eye Tracking in human-computer interaction and usability research: ready to deliver
the promises,” Minds Eye, vol. 2, no. 3, pp. 573–605, 2003.
[5]. O. Ferhat and F. Vilarino, “Low cost eye tracking: the current panorama,” Computational Intelligence and
Neuroscience, vol. 2016, Article ID 8680541, pp. 1–14, 2016.
[6]. Tobii EyeX, “EyeX,” 2014, http://www.tobii.com/eyex.
[7]. GazePoint, “Gazept,” 2013, http://www.gazept.com/category/gp3-eye-tracker
[8]. The eyeTribe, “EyeTribe,” 2014, http://www.theeyetribe.com.
[9]. M. A. Eid, N. Giakoumidis, and A. El Saddik, “A novel eye-gaze-controlled wheelchair system for navigating
unknown environments: case study with a person with ALS,” IEEE Access, vol. 4, pp. 558–573, 2016
[10]. L. Sun, Z. Liu, and M.-T. Sun, “Real time gaze estimation with a consumer depth camera,” Information Sciences,
vol. 320, pp. 346–360, 2015.

© IJIREEICE This work is licensed under a Creative Commons Attribution 4.0 International License 124