Research on the Improvement of MTCNN ALGORITHM: Face Recognition with Mask

Xiao, J.; Wang, J.; Cao, S.; Li, Y.

During the 2019-nCoV epidemic, in order to effectively prevent the spread of the virus, people generally wore masks when entering public places, rendering traditional facial recognition technology ineffective. This paper constructs a dataset of face images with masks, and proposes a face recognition algorithm for masks based on deep learning. Applying the TensorFlow framework and proposing an improved MTCNN algorithm to cluster the effective feature regions of the face;using the FaceNet model shortens the time of face detection and improves the efficiency of face recognition. The test results show that the improved model has an average accuracy of 91% in recognition of faces wearing masks, and an average recall rate of 92%. Compared with the unimproved algorithm, the candidate frame of the improved algorithm focuses on important feature information to make it accurate. The rate increased by an average of 3%. © 2021 ACM.