Evaluation of VDT-Induced Visual Fatigue by Automatic Detection of Blink Features
Zhijie Yin,
Bing Liu,
Dongmei Hao,
Lin Yang,
Yongkang Feng
Affiliations
Zhijie Yin
Faculty of Environment and Life, Beijing University of Technology, and Beijing International Science and Technology Cooperation Base for Intelligent Physiological Measurement and Clinical Transformation, Beijing 100124, China
Bing Liu
Ophthalmology Department, The University Hospital of Beijing University of Technology, Beijing 100124, China
Dongmei Hao
Faculty of Environment and Life, Beijing University of Technology, and Beijing International Science and Technology Cooperation Base for Intelligent Physiological Measurement and Clinical Transformation, Beijing 100124, China
Lin Yang
Faculty of Environment and Life, Beijing University of Technology, and Beijing International Science and Technology Cooperation Base for Intelligent Physiological Measurement and Clinical Transformation, Beijing 100124, China
Yongkang Feng
Faculty of Environment and Life, Beijing University of Technology, and Beijing International Science and Technology Cooperation Base for Intelligent Physiological Measurement and Clinical Transformation, Beijing 100124, China
This study evaluates the progression of visual fatigue induced by visual display terminal (VDT) using automatically detected blink features. A total of 23 subjects were recruited to participate in a VDT task, during which they were required to watch a 120-min video on a laptop and answer a questionnaire every 30 min. Face video recordings were captured by a camera. The blinking and incomplete blinking images were recognized by automatic detection of the parameters of the eyes. Then, the blink features were extracted including blink number (BN), mean blink interval (Mean_BI), mean blink duration (Mean_BD), group blink number (GBN), mean group blink interval (Mean_GBI), incomplete blink number (IBN), and mean incomplete blink interval (Mean_IBI). The results showed that BN and GBN increased significantly, and that Mean_BI and Mean_GBI decreased significantly over time. Mean_BD and Mean_IBI increased and IBN decreased significantly only in the last 30 min. The blink features automatically detected in this study can be used to evaluate the progression of visual fatigue.
