Blinking supervision in a working environment

• Published in: Journal of biomedical optics Vol. 21; no. 2; p. 025005
• Main Authors: Morcego, Bernardo, Argilés, Marc, Cabrerizo, Marc, Cardona, Genís, Pérez, Ramon, Pérez-Cabré, Elisabet, Gispets, Joan
• Format: Journal Article Publication
• Language: English
• Published: United States Society of Photo-Optical Instrumentation Engineers 01.02.2016
• Subjects: Adnexa oculi; Algorismes; Algorithms; Annexos; Automatic control; automatic eye blink detection; Automàtica i control; Blinking - physiology; blinking frequency; Ciències de la visió; computer vision syndrome (CVS); Control automàtic; dry eye; Dry Eye Syndromes; Humans; image processing algorithm; Image Processing, Computer-Assisted - methods; Informàtica; Iris - physiology; Ulls; video display terminal (VDT); webcam; Workplace; Àrees temàtiques de la UPC; Òptica física; automatic eye blink detection; image processing algorithm; webcam; blinking frequency; computer vision syndrome; dry eye; video display terminal
• ISSN: 1083-3668; 1560-2281
• DOI: 10.1117/1.JBO.21.2.025005

The health of the ocular surface requires blinks of the eye to be frequent in order to provide moisture and to renew the tear film. However, blinking frequency has been shown to decrease in certain conditions such as when subjects are conducting tasks with high cognitive and visual demands. These conditions are becoming more common as people work or spend their leisure time in front of video display terminals. Supervision of blinking frequency in such environments is possible, thanks to the availability of computer-integrated cameras. Therefore, the aim of the present study is to develop an algorithm for the detection of eye blinks and to test it, in a number of videos captured, while subjects are conducting a variety of tasks in front of the computer. The sensitivity of the algorithm for blink detection was found to be of 87.54% (range 30% to 100%), with a mean false-positive rate of 0.19% (range 0% to 1.7%), depending on the illumination conditions during which the image was captured and other computer-user spatial configurations. The current automatic process is based on a partly modified pre-existing eye detection and image processing algorithms and consists of four stages that are aimed at eye detection, eye tracking, iris detection and segmentation, and iris height/width ratio assessment.