External face recognition device of a monitoring camera

Abstract

The invention provides an external face recognition device of a monitoring camera. The external face recognition device comprises a video input interface, a digital video controller, a face image preprocessing module, a face image recognition and comparison module, and a network interface. The video input interface transmits a video stream output by the monitoring camera to the digital video controller; the digital video controller sends a digital image to the face image preprocessing module; the face image preprocessing module sends a standardized face image to the face image recognition andcomparison module; and the face image recognition and comparison module sends face recognition information to the network interface. According to the invention, a common monitoring camera is upgradedto a monitoring camera with an independent face recognition function at a low cost; the face recognition and comparison can be independently completed without a face recognition server, the cost of face recognition equipment can be reduced, the space occupied by the equipment is reduced, the adaptability to the environment is improved, the transmission efficiency is improved, and the safety of a face recognition system is improved.

Description

technical field [0001] The invention relates to the field of surveillance cameras, in particular to an external face recognition device for a surveillance camera. Background technique [0002] In recent years, the face recognition technology based on neural network has developed rapidly. Compared with the previous face recognition technology, the recognition rate of face recognition technology based on neural network has been qualitatively improved, and it has reached more than 99%. Compared with other biometric identification technologies, face recognition technology has unique advantages in practical applications: images containing faces can be directly acquired through video or image acquisition equipment for identification; the entire identification process does not require physical contact and is fast and fast. At present, face recognition technology based on neural network has been widely used in various fields such as finance, education, tourism, and public safety. ...

AI Technical Summary

Problems solved by technology

Therefore, the common problem of existing neural network-based face recognition equipment is that the equipment does not have an independent face recognition function and relies on the face recognition server, that is, it needs to transmit the collected video or image to the face recognition server. The server, which completes the comparison of face features to realize face recognition

The main defect of the above-mentioned second solution is that the face recognition function relies on the remote network transmission of video or images, which will consume a large amount of network bandwidth; when the transmission is unstable due to network delay and network congestion, the face recognition function of the device will change. If the network communication between the face recognition device and the face recognition server is cut off artificially or interrupted due to a fault, the face recognition function will be directly unavailable

In addition, both of the above two technical solutions will incur the purchase or rental cost of the face recognition server, and the simultaneous operation of the face recognition server and auxiliary support equipment will also consume additional energy, space and labor costs

Images