Face recognition access control processing method, gate, control terminal and system

Abstract

The invention relates to a face recognition access control processing method, a gate, a control terminal, a system, a computer device, and a storage medium. The method comprises the steps of: a firstgate detects a human face and calculates a feature value of the human face, sends the feature value of the human face to a second gate, while the first gate compares the feature value of the human face with a first sub-human face database stored in the first gate, the second gate compares the feature value of the human face with a second sub-human face database stored in the second gate and feedsback a comparison result to the first gate. The parallel calculation of the two gates improves the calculation efficiency and the utilization rate of the gate CPU, at the same time, the transmission of the feature value of the human face and the result feedback are local communications, and the communication efficiency is high, so that the efficiency of face recognition of the access control gateis improved.

Description

technical field [0001] The present application relates to the technical field of artificial intelligence, in particular to a load-balanced face recognition access control processing method, a gate, a control terminal, a system, a computer device and a storage medium. Background technique [0002] With the development of face recognition technology, this technology has been gradually applied in the entrance and exit access control security management system. By taking the face image of the person entering the entrance area of ​​the gate, the facial features of the person are extracted from the face image. The information is compared with the face in the remote server or the local face database of the gate, and the access control security management system finally makes a judgment on whether to open the door. [0003] However, in the face recognition method applied to the access control safety management system in the related art, there are multiple passages equipped with gate...

AI Technical Summary

Problems solved by technology

[0003] However, in the face recognition method applied to the access control safety management system in the related art, there are multiple passages equipped with gates at the entrance and exit. Each gate in these gates is a separate computing unit, although each gate The intelligent server connected to the cloud platform can support large-capacity face library comparison, but only using the cloud platform for face recognition, due to the time required for the gate to communicate with the cloud platform, the speed of opening the gate will be slow; and the In the method, it will take a long time for a single gate to open the door from the recognition of the face to the next capture of the face to open the door. The CPU of the gate is idle during this period, and the CPU computing resources of the gate will be wasted. The process of face recognition to open the door is not efficient

[0004] Aiming at the problem that the face recognition method of the access control system is not efficient in related technologies, no effective solution has been proposed yet

Images