A method, apparatus, compute device and storage medium for in vivo detection

Abstract

The invention relates to a living body detection method, a device, a computer device and a storage medium. The method comprises obtaining a face image; detecting a face image to obtain a face region to be measured; analyzing the area of face to be measured, according to the result of analysis, judging the living face, the living face defense and the three-dimensional face mask defense, obtaining the judging result; outputting a decision result. As the color image and the infrared depth image are acquired, by using depth-learning model to detect human face in color image, combined with the analysis of the screen pixel texture of the face region to be measured, a Surf algorithm is adopted to determine whether the face region to be tested meets preset conditions, in order to improve the anti-attack ability of 3D simulation mask, video and general picture, effective defense mask, 3D simulation face, video non-live attack, and greatly improve the accuracy of face recognition.

Description

technical field [0001] The present invention relates to living body detection, and more specifically refers to a living body detection method, device, computer equipment and storage medium. Background technique [0002] With the continuous development of deep learning and artificial intelligence technology, face recognition systems are more and more used in security, smart new retail, finance, subways, hotels, airports and other scenarios that require identity verification, such as remote bank account opening, wireless Renchao merchants automatically complete payment by swiping face, access control system, subway face swiping payment, airport automatic verification of witnesses, etc. In these high-level security application areas, especially those related to money-related fields such as face payment, in addition to ensuring that the face similarity of the verified person conforms to the data stored in the database, it is also necessary to confirm that the verified person is ...

AI Technical Summary

Problems solved by technology

At present, the 3D liveness detection technology products on the market do not have a recognized and mature living body verification scheme. The existing 3D liveness detection technology is almost completely dependent on hardware devices, such as infrared cameras and depth cameras, and can only prevent static photo attacks. 3D masks, high-definition Video attack doesn't work well

Chinese patent 201580000356.8 discloses a living body detection method, equipment, and computer program products, specifically detecting human face movements from captured images, and performing liveness detection ba

Images