Eye State Recognizer Using Light-Weight Architecture for Drowsiness Warning

Abstract

The eye are a very important organ in the human body. The eye area and eyes contain lots of useful information about human interaction with the environment. Many studies have relied on eye region analyzes to build the medical care, surveillance, interaction, security, and warning systems. This paper focuses on extracting eye region features to detect eye state using the light-weight convolutional neural networks with two stages: eye detection and classification. This method can apply on simple drowsiness warning system and perform well on Intel Core I7-4770 CPU @ 3.40 GHz (Personal Computer - PC) and on quad-core ARM Cortex-A57 CPU (Jetson Nano device) with 19.04 FPS and 17.20 FPS (frames per second), respectively.