Communications of the ACM
Software Turns Webcams Into Eye Trackers
Researchers at Brown University have developed software to determine which parts of a Web page are attracting users' eyes.
Credit: iStock
Brown University researchers have created WebGazer.js, software designed to help website owners and developers determine which parts of a Web page are attracting users' eyes.
The software turns integrated computer webcams into eye trackers that can infer where on a Web page a user is looking.
"We're using the webcams that are already integrated in users' computers, which eliminates the cost factor, and it's more naturalistic in the sense that we observe people in the real environment instead of in a lab setting," says Brown University Ph.D. candidate Alexandra Papoutsaki.
The code, which is embedded on a website, prompts users to give permission to access their webcams. After permission is given, the software uses a face-detection library to locate the user's face and eyes, and then converts the image to black and white, enabling it to distinguish the whites of the eyes from the iris. The system then uses a statistical model calibrated by the user's clicks and cursor movements, assuming a user looks at the spot where they click, so each click tells the model what the eyes look like when they are viewing a particular spot.
It requires three clicks to get a reasonable calibration, after which WebGazer.js can accurately infer the location of the user's gaze in real time.
From News from Brown
View Full Article
Abstracts Copyright © 2016 Information Inc., Bethesda, Maryland, USA
No entries found