A human video database for facial feature detection under spectacles with varying alertness levels

Pressing demand of workload along with social media interaction leads to diminished alertness during work hours. Researchers attempted to measure alertness level from various cues like EEG, EOG, Video-based eye movement analysis, etc. Among these, video-based eyelid and iris motion tracking gained much attention in recent years. However, most of these implementations are tested on video data of subjects without spectacles. These videos do not pose a challenge for eye detection and tracking. In this work, we have designed an experiment to yield a video database of 58 human subjects wearing spectacles and are at different levels of alertness. Along with spectacles, we introduced variation in session, recording frame rate (fps), illumination, and time of the experiment. We carried out analysis to detect the reliableness of facial and ocular features like yawning and eyeblinks in the context of alertness level detection capability. Also, we observe the influence of spectacles on ocular feature detection performance under spectacles and propose a simple preprocessing step to alleviate the specular reflection problem. Extensive experiments on real-world images demonstrate that our approach achieves desirable reflection suppression results within minimum execution time compared to the state of the art.