Driver fatigue recognition based on facial expression analysis using local binary patterns

Abstract

Driver fatigue is a major cause of traffic accidents. Automatic vision-based driver fatigue recognition is one of the most prospective commercial applications based on facial expression analysis technology. Deriving an effective face location from original driver face images is a vital step for successful fatigue facial expression recognition. In this paper, we empirically adopt fast and robust face detection algorithm to describe and normalizing facial expression images. We evaluate facial representation based on statistical local features, Local Binary Patterns, for person-independent fatigue facial expression recognition, and observe that LBP features perform stably and robustly over a useful range of fatigue face images. Moreover, we adopt AdaBoost to learn the most discriminative fatigue facial LBP features from a large LBP feature pool, which is a critical problem but seldom addressed in the existing work. We observe in our experiments that Boost-LBP features perform stably and robustly, and best recognition performance is obtained by using SVM with Boost-LBP features.