Improvement And Research Of Facial Expression Recognition Algorithm Is Applied In The Emotional Intelligent Classroom

The "Internet plus" concept has been applied to many aspects, it is linked to various industries. The Internet provides information support to make more innovation and development. For example, the Internet can be applied to education, we can choose teachers or schools to facilitate teaching. Therefore, the old way of education can’t meet the need of modern society. In view of education problems, the system, "Internet plus classroom", development can feedback teaching effect -- intelligent classroom.In this paper, facial expression recognition captures the classroom response of students in real time, the final summary and analysis for teacher’s reference help for improving the teaching level. Also, the school has large demand for hydro-electric power, and a large amount of waste. Through the scientific theory basis, light and air conditioning temperature achieve automatic control for students to create a good learning environment, while reducing waste.At this stage, the expression recognition technology has been quite mature, the recognition rate is high, but the calculation is large, the calculation efficiency is not high so that it is limited development. Thus, this paper proposes a facial expression recognition method, which can improve the recognition rate based on the recognition rate. Details are as follows:(1) Using the frame difference method to improve the speed of face detection for video. That is based on the frame difference between adjacent frames, to determine whether there are active regions, the use of active regions to narrow the" range of human face detection, the use of SVM classification method for the detection of human face region. It is found that this method is a feature extraction method which can simplify the calculation process and shorten the processing time.(2) In the process of feature extraction, LBP is used as a method of extracting feature vector, and the difference between the frame and the operation of the two values of the process. So, by the appropriate choice of threshold before the detection of human face region, we can get high quality of the two value of the image. This feature extraction can reduce duplication, to meet the needs of embedded real-time.(3) At last, through the simulation experiment, the improved expression recognition algorithm can reduce the computation time, and the recognition rate compared to the basic no change.The realization of the system, realize the face recognition and the control of the equipment in the classroom, that is, the image of the face in the video to do the face recognition, and the results of the preservation and analysis. Through hardware protocol configuration, program recording, to acquire data of the temperature, humidity, brightness, the switch control equipment and so on, pictures, video shooting. The improved face recognition algorithm is applied to the system, which has a good processing speed, and the system can save energy to the maximum extent under the premise of providing comfort.