This is a Python (2 and 3) library that provides a webcam-based eye tracking system. It gives you the exact position of the pupils and the gaze direction, in real time.

🚀 Quick note: I'm looking for job opportunities as a software developer, for exciting projects in ambitious companies. Anywhere in the world. Send me an email!

Clone this project:

git clone https://github.com/antoinelame/GazeTracking.git

Install these dependencies (NumPy, OpenCV, Dlib):

pip install -r requirements.txt

The Dlib library has four primary prerequisites: Boost, Boost.Python, CMake and X11/XQuartx. If you doesn't have them, you can read this article to know how to easily install them.

Run the demo:

python example.py

import cv2
from gaze_tracking import GazeTracking

gaze = GazeTracking()
webcam = cv2.VideoCapture(0)

while True:
    _, frame = webcam.read()
    gaze.refresh(frame)

    new_frame = gaze.annotated_frame()
    text = ""

    if gaze.is_right():
        text = "Looking right"
    elif gaze.is_left():
        text = "Looking left"
    elif gaze.is_center():
        text = "Looking center"

    cv2.putText(new_frame, text, (60, 60), cv2.FONT_HERSHEY_DUPLEX, 2, (255, 0, 0), 2)
    cv2.imshow("Demo", new_frame)

    if cv2.waitKey(1) == 27:
        break

In the following examples, gaze refers to an instance of the GazeTracking class.

gaze.refresh(frame)

Pass the frame to analyze (numpy.ndarray). If you want to work with a video stream, you need to put this instruction in a loop, like the example above.

gaze.pupil_left_coords()

Returns the coordinates (x,y) of the left pupil.

gaze.pupil_right_coords()

Returns the coordinates (x,y) of the right pupil.

gaze.is_left()

Returns True if the user is looking to the left.

gaze.is_right()

Returns True if the user is looking to the right.

gaze.is_center()

Returns True if the user is looking at the center.

ratio = gaze.horizontal_ratio()

Returns a number between 0.0 and 1.0 that indicates the horizontal direction of the gaze. The extreme right is 0.0, the center is 0.5 and the extreme left is 1.0.

ratio = gaze.vertical_ratio()

Returns a number between 0.0 and 1.0 that indicates the vertical direction of the gaze. The extreme top is 0.0, the center is 0.5 and the extreme bottom is 1.0.

gaze.is_blinking()

Returns True if the user's eyes are closed.

frame = gaze.annotated_frame()

Returns the main frame with pupils highlighted.

Your suggestions, bugs reports and pull requests are welcome and appreciated. You can also starring ⭐️ the project!

If the detection of your pupils is not completely optimal, you can send me a video sample of you looking in different directions. I would use it to improve the algorithm.

This project is released by Antoine Lamé under the terms of the MIT Open Source License. View LICENSE for more information.