Face recognition method based on 5G network

Abstract

The invention belongs to the technical field of face recognition, and particularly discloses a face recognition method based on a 5G network, and the method comprises the steps of collecting a face dynamic video of a to-be-recognized person through a collection device; uploading the acquired human face dynamic video to a cloud server in a 5G network state; decomposing the human face dynamic videoframe by frame on a cloud server, and forming a human face image set according to a frame number sequence; preprocessing each face image in the face image set; extracting human face feature points oneach preprocessed human face image; recognizing each face image one by one through the face feature points on each face image; and obtaining the face recognition degree of each face image, comparing each face recognition degree with a preset face recognition threshold, and ending the recognition when the number of the face recognition degrees higher than the preset face recognition threshold is greater than or equal to 50% of the total amount of the face image set.

Description

technical field [0001] The invention relates to the technical field of face recognition, in particular to a face recognition method based on a 5G network. Background technique [0002] The face recognition technology is based on the facial features of the person. For the input face image, it first judges whether there is a face. If there is a face, it further gives the position, size and each major facial organ of each face. location information. Based on this information, the identity features contained in each face are further extracted, and compared with known faces, so as to identify the identity of each face. [0003] In the existing methods of face recognition, due to the limitation of data transmission, most of the face images are collected and uploaded to the cloud after compression, and then feature recognition can be performed, but a single face image is prone to generation Recognition errors, and liveness detection cannot be performed for a single face image, an...

AI Technical Summary

Problems solved by technology

[0003] In the existing methods of face recognition, due to the limitation of data transmission, most of the face images are collected and uploaded to the cloud after compression, and then feature recognition can be performed, but a single face image is prone to generation Recognition errors, and liveness detection cannot be performed for a single face image, and if a large number of face images are collected, the upload time and recognition time will increase, which will reduce the user experience of the person to be recognized, and will also affect the face. Recognition efficiency

Images