Eye recognition in near-infrared images for driver's drowsiness monitoring

The paper presents a system for driver's eye recognition from near infrared (NIR) images. The system is organized in a cascade of two classification modules. The first one is responsible for initial eye detection and the second one for eye validation. Detection is based on a novel eye model suited for the NIR images. This process is augmented by the background subtraction module. The subsequent stage of eye validation is performed by the second classifier based on the higher-order decomposition of a tensor with geometrically deformed prototypes. Obtained results in day and night conditions show high accuracy and real-time processing of the system in software implementation.