Capturing and evaluating blinks from video-based eyetrackers

Abstract

Blinks are related to several emotional states, and the present report describes a simple, reliable way to measure blinks from the video stream of an eye obtained during eyetracking, where the source of the eye video is a video camera attached to a head-mounted eyetracker. Computer vision techniques are employed to determine the moments that a blink starts and ends, for the purpose of calculating blink frequency and duration. The video is first processed to show blocks of eyelid and pupil movements, and is then analyzed for blink starts and ends. The moment of a blink start is reported when the eyelid starts to move quickly, exceeding a predetermined threshold. The end of a blink arises when the pupil size increases by less than a separate threshold. We observed several different blink patterns from different subjects, and our algorithm was designed to work for all of these patterns. We evaluated our algorithm by manually measuring the true blinks of five different subjects while they were eyetracked. To test the sensitivity and specificity of the algorithm, we employed a series of threshold values to plot the receiver operating characteristic curves. Using the best thresholds, we achieved excellent sensitivity (>90 %) and specificity (>99 %) over the five subjects. Potential applications of this research include real-time, nonintrusive, continuous and automated measurements of mental workload and other emotional states related to blink rates and durations.

Blinking supervision in a working environment

“…The mean TPR was 87.54% and the mean FPR was 0.19%, in accordance with the published report by Jiang and co-workers 10 . The range of TPR was from 30% to 100% and the range of FPR was from 0 to 1.7%.…”

“…This algorithm is inspired by the work of Jiang et al, 2013 10 , although several important modifications were implemented. First, the luminosity of the image is normalized using a 31x31 pixel median filter, after which the Otsu 18 optimal threshold binarisation is applied.…”

“…Similarly, Himebaugh et al, evaluated SEBR whilst participants conducted a series of low to high levels of concentration on VDT tasks (looking at a blank computer screen or watching a film, and playing a computer game or viewing a series of rapidly changing letters, respectively) 7 . They observed a Similarly, Jiang et al, 2013, were able to detect the beginning and the end of an eyeblink 10 . The difference between two consecutive frames was binarised and morphological operations were employed to determine the presence of the iris.…”

Workload assessment of surgeons: correlation between NASA TLX and blinks

“…The high-quality image of the eye enabled us to compute the number of blinks and report blink durations. As we reported elsewhere, the accuracy of this algorithm can be as high as 98 % when compared to the detection by human operators using video [20].…”

“…In the postoperative phase, a custom-designed algorithm was applied to the eyemotion videos to compute the number of blinks, as we previously described [20]. The algorithm was developed on the basis of computer vision techniques.…”