RealEye Accuracy on Smartphones
Learn how RealEye ensures accurate webcam eye-tracking on Smartphones
Using Smartphones creates unique challenges for eye-tracking because users handle their phones in many different ways. Unlike desktops, where the screen stays in one position, people often change how they hold their devices, or move them closer or farther away from their faces. RealEye’s system adapts to these conditions to provide reliable gaze tracking, with consideration to how users interact with their phones.
Evaluating the Accuracy of RealEye on Smartphones
The Accuracy means how close the system’s prediction is to the actual point on the screen where a person is looking. To evaluate the Accuracy of RealEye on Smartphones, we performed a validation study that involved grid-based tasks (learn more in our Whitepaper). The study was performed in a vertical orientation, as RealEye currently does not support studies in a horizontal orientation.
The results of the study showed that the average accuracy on Smartphones is ≈ 56 pixels. This means that, on average, the system’s prediction is within ~1/6 of the screen’s width and ~1/10 of the screen’s height.
For 71% of the cases, fixations landed within 75 pixels of the target center, 87% were within 100 pixels, and 95% were within 125 pixels. These results indicate that RealEye’s system performs reliably even in the dynamic environment of smartphone use.
The Importance of Accuracy When Creating AOIs
Areas of Interest (AOIs) are predefined sections of the screen that researchers focus on during an eye-tracking study. For example, AOIs might include buttons, menus, or specific sections of content.
The Accuracy of the eye-tracking system impacts the size of defined AOIs. To minimize misclassification errors, AOIs should be large enough to accommodate the system's accuracy, but not so large that they include irrelevant parts of the screen. Based on RealEye’s system performance on Smartphones, minimum AOI size cover approximately 16-17% of the width and 10% of the height of the displayed content to ensure reliable fixation detection.
💌 If you have any questions or need further assistance, feel free to reach out to our team at contact@realeye.io