Human face living body detection method and device, computing equipment and computer storage medium

Abstract

The embodiment of the invention relates to the technical field of image processing, and discloses a human face living body detection method and device, computing equipment and a computer storage medium. The method comprises the following steps: acquiring a video image for user face recognition; intercepting continuous frames of images for face recognition according to the video image; and performing picture compression on each continuous frame of image to form a picture stream, and transmitting the picture stream to a server for recognition processing. By means of the mode, according to the embodiment of the invention, through separation of the front end and the rear end, a more reliable action instruction determination mode is realized, and the safety and the real-time performance of living body detection application are improved.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of image processing, and in particular to a human face liveness detection method, device, computing device, and computer storage medium. Background technique [0002] Face recognition has been widely used in finance, security, e-commerce and other fields. Face recognition is a type of biometric recognition. Compared with fingerprint recognition, which is easily affected by foreign matter such as sweat, and iris recognition equipment, the equipment requirements are too high. Face recognition has huge advantages. However, human faces are very easy to copy by means of photos, videos, masks, etc., which brings huge security risks to the face authentication system. As a result, living body detection technology has emerged. Liveness detection technology can identify whether the person in the image or video is a real person based on information such as human head movement, blinking, thermal ...

AI Technical Summary

Problems solved by technology

[0004] In the process of realizing the embodiment of the present invention, the inventors found that: for the living body detection method that requires additional hardware, its disadvantages are high cost and inconvenient use

Although the motion detection method does not need to rely on other hardware other than ordinary cameras, the main disadvantage is that the mainstream methods include front-end and back-end

The front-end deploys the core algorithm on the client, which makes the application easy to be tampered with, or can be faked through pre-recorded facial movement videos or photos, which poses a large security risk

The back-end type deploys the core algorithm on the server side, but needs to transmit the entire video, the network overhead is large, and the real-time performance is poor

Images