Developed by computer scientists at Brown University, WebGazer.js can be added to any site with just a few lines of code. Running on a website visitor's browser, it essentially turns the computer's webcam into an eye-tracker that can infer where on a page the viewer is looking.
Ultimately, it could help Web developers optimize content and make their websites more user-friendly.
Once embedded on a website, Brown's software first prompts users to give permission to access their webcams. Once permission is given, the software employs a face-detection library to locate the user’s face and eyes. The system then converts the image to black and white, enabling it to distinguish the whites of the viewer's eyes from the iris.
Having located the iris, the system employs a statistical model that is calibrated by the user’s clicks and cursor movements. The model assumes that a user looks at the spot where they click, so each click tells the model what the eye looks like when it’s viewing a particular spot.
It takes about three clicks to get a reasonable calibration, Brown says. After that, the model can accurately infer the location of the user’s gaze in real time.
“We see this as a democratization of eye-tracking,” said Alexandra Papoutsaki, a Brown University graduate student who led the development of the software. “Anyone can add WebGazer to their site and get a much richer set of analytics compared to just tracking clicks or cursor movements.”
For privacy reasons, no video is shared, Brown said. Only the locations of the user’s gaze are reported back to the website.
Papoutsaki and her colleagues performed a series of experiments to evaluate the system. They showed that it can infer gaze location within 100 to 200 screen pixels. That’s not as accurate as specialized commercial eye trackers, but it still offers a pretty good estimation of where the user is looking.
Overall, it could help website developers prioritize popular or eye-catching content, optimize a page’s usability, or place and price advertising space. Further ahead, potential applications could include eye-controlled gaming or broader accessibility.
Papoutsaki and her colleagues will present a paper describing the software at the International Joint Conference on Artificial Intelligence in July. In the meantime, the code is freely available to anyone who wants to test it out.