A discriminative target equation-based face recognition method for teaching attendance (Q2064734)

Summary: In this paper, we use discriminative objective equations to conduct an in-depth study and analysis of face recognition methods in teaching attendance and use the model in actual teaching attendance. It focuses on the design and implementation of the attendance module, which uses wireless network technology to record students' access to classrooms in real time, and relies on face recognition technology to identify students' sign-in images to achieve attendance records of students' independent attendance sign-in. Real-time detection of student attendance is achieved by combining face detection and face recognition technology through regular camera photography and automatic attendance check-in by the server. Based on the recognition results of the attendance check-in image, an attendance mechanism is proposed, and the attendance score of the student for the current course can be calculated using the attendance mechanism, which realizes the automatic management of student attendance. For the face recognition process, the system uses the Ad boost algorithm based on Hear features to achieve face detection, preprocesses the face samples with gray normalization, rotation correction, and size correction, and uses the method based on LBP features to achieve face recognition. Firstly, a combination of histogram equalization and wavelet denoising is chosen to preprocess the training sample images to obtain the face image light invariance description, and then, the initial dictionary is constructed using the dimensionality reduction performance of the PCA method; next, the initial dictionary is updated, and a new dictionary with representation and discrimination capabilities is obtained using the LC-KSVD algorithm that makes improvements in the dictionary update stage. The sparse coefficients of the feature matrix of the test sample image under the new dictionary are calculated, and the class correlation reconstruction is performed on the feature matrix of the test sample image, and the corresponding reconstruction error is solved; finally, the discriminative classification of the test sample image is achieved according to the solved class correlation reconstruction error. The relevant experiments on the face database prove that the algorithm can improve the recognition accuracy to a certain extent and better solve the influence of changing lighting conditions on the face recognition accuracy.