Facial expression recognition method based on intelligent accompanying robot

The invention belongs to the technical field of video monitoring, and relates to a facial expression recognition method. The method comprises the steps of preprocessing a to-be-detected video image; carrying out face detection on the preprocessed video frame by adopting a face detection algorithm to obtain face information; and recognizing the detected facial expression of the human face, and outputting a recognition result. According to the method, the face detection method combining multiple cascade classifiers is adopted, multiple different features of the input image are extracted and combined with different classifiers, more accurate face positions and the total number of faces in the image can be obtained, the detection accuracy is high and false detection is less; a deep convolutional network model used for expression recognition is self-built; an Adam algorithm is adopted to optimize a loss function, the speed is high, the learning efficiency is high, and the common problems that the learning rate dis