Description

Fatigue-driving detection, which employs pattern recognition measure to discover driver’s fatigue stat, is considered as a key technique to improve road safety. However, the widely used frontal face recognition systems bring some problems, such as low recognition accuracy, poor real-time ability, and high algorithm complexity. As a very efficient supplement, in this paper, a new color space modeling, which uses multi-threshold as decision criteria, is raised to enhance face skin extraction performance, while a three steps strategy is designed to eliminate noise and other adverse effects. Experiments results show that proposed algorithm could extract side face contour line effectively and should provide scientific basis for fatigue state’s real-time tracking application.