Research On Fatigue Driving Recognition Method Based On Facial Expression

While the car is convenient for us,it also raises a series of traffic safety issues.In many traffic accidents,driver fatigue driving is one of the main reasons.At present,the monitoring of the fatigue state of the driver during driving has become an important research topic.It is not only an important preventive measure for effectively reducing the incidence of traffic accidents,but also an important content for realizing the intelligentization of automotive equipment and has a very high social value.In this paper,facial expression is taken as the research object,and the fatigue driving recognition scheme is designed.The Convolutional Neural Network(CNN)is used to build a suitable network model to train learning fatigue expression features.The fatigue expression images are obtained through the following three ways: first,writing a crawler code,searching for a face fatigue expression image on a webpage;second,selecting part of the images in different facial expression data sets;third,taking fatigue expression photos.Normalize the acquired images and build the database.In order to improve the accuracy and real-time of recognition,the image is subjected to grayscale and histogram equalization preprocessing operations.Combining haar-like features and Adaboost algorithm,the face region is extracted from the complex background,and the face in the picture information is detected.The convolutional neural network model is designed,and the detected face image is input into the model,and the parameters are adjusted to realize the recognition of the driver’s fatigue expression.The experimental results show that the convolutional neural network model designed in this paper can complete the training of fatigue expression features,and has a high recognition accuracy and real-time performance for driver fatigue expression,which helps to reduce the incidence of traffic accidents.