RESUMO
As the use of electronic displays increases rapidly, visual fatigue problems are also increasing. The subjective evaluation methods used for visual fatigue measurement have individual difference problems, while objective methods based on bio-signal measurement have problems regarding motion artifacts. Conventional eye image analysis-based visual fatigue measurement methods do not accurately characterize the complex changes in the appearance of the eye. To solve this problem, in this paper, an objective visual fatigue measurement method based on infrared eye image analysis is proposed. For accurate pupil detection, a convolutional neural network-based semantic segmentation method was used. Three features are calculated based on the pupil detection results: (1) pupil accommodation speed, (2) blink frequency, and (3) eye-closed duration. In order to verify the calculated features, differences in fatigue caused by changes in content color components such as gamma, color temperature, and brightness were compared with a reference video. The pupil detection accuracy was confirmed to be 96.63% based on the mean intersection over union. In addition, it was confirmed that all three features showed significant differences from the reference group; thus, it was verified that the proposed analysis method can be used for the objective measurement of visual fatigue.
Assuntos
Astenopia/diagnóstico por imagem , Piscadela , Processamento de Imagem Assistida por Computador , Pupila , Humanos , Raios Infravermelhos , Redes Neurais de ComputaçãoRESUMO
Eye fatigue is a common health problem across all age groups. Herein, we explored the correlation between eye fatigue and thickness of the retinal nerve fiber layer (NFL). Included in the NFL are intrinsically photosensitive retinal ganglion cells (ipRGCs), which are associated with trigeminal pain. This retrospective cross-sectional study included outpatients with best-corrected visual acuity above 20/30 in both eyes and without dry eye, glaucoma, or retinal disease. A total of 1981 patients were initially enrolled and 377 patients were declared as eligible for the study analysis. We tested subjects for the presence of major ocular symptoms and measured thickness of ganglion cell complex (GCC) using optical coherence tomography. A total of 377 outpatients (46.4% men, mean age of 57.1 years) were enrolled for analysis, based on the interview-reported prevalence of six eye symptom, as follows: 31.5% for eye fatigue, 19.2% for blurring, 18.6% for dryness, 15.7% for photophobia, 13.5% for irritation, and 4.6% for pain. The macular GCC was significantly thicker in subjects with eye fatigue compared to the group not reporting eye fatigue (103.8 µm versus 100.3 µm, P = 0.014). Regression analysis identified eye fatigue (P = 0.026, ß=0.122, adjusted for age and sex) and dryness (P =0.024, ß=0.130) as significantly correlated with the macular GCC thickness, while the full macular thickness showed no significant correlation. In conclusions, eye fatigue and dryness were positively associated with thickness of the macular GCC. Nonvisual symptoms might therefore play a role in the development of eye fatigue.