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 Essential Oils 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), Collections 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.