Living body human face recognition method and device

Abstract

The invention relates to the technical field of identity verification, and particularly relates to a living body human face recognition method, a device and a system. The method comprises steps: multiple human face images are acquired instantly; according to the human face images, a fixation point of at least one eye in each human face image or a motion track of the fixation point is acquired; according to the fixation point of the eye or the motion track of the fixation point, whether the eye moves according to a hint is judged; if yes, living body verification is passed. According to the method, when a user carries out facial feature verification, the eye moves according to the hint; as facial features and eye moving data are extracted from the same picture or one group of pictures or video, an illegal logon person can not cheat the verification device by using a face image or video prepared in advance, and thus, the method can judge that the user agrees to the face features, and the face information is from the living body in reality.

Description

technical field [0001] The present invention relates to the technical field of identity verification, in particular to a living face recognition method and device. Background technique [0002] Currently, facial recognition technology is widely used for identity verification in secure login systems. The current facial recognition technology generally obtains the current user's facial photo in real time through image acquisition equipment, and compares the facial photo obtained in real time with the previously stored facial photo based on the characteristics and distribution of facial features. If the comparison is consistent, the identity verification pass. [0003] However, in the process of facial recognition, illegal registrants can "deceive" cameras or other image acquisition devices by forging faces, so that the photos acquired by the image acquisition devices are not photos of living faces. For example, if the registrant's face photo or face video clip is placed in f...

AI Technical Summary

Problems solved by technology

[0003] However, in the process of facial recognition, illegal registrants can "deceive" cameras or other image acquisition devices by forging faces, so that the photos acquired by the image acquisition devices are not photos of live faces

For example, if the registrant's face photo or face video clip is placed in front of the image acquisition device, the current user's face photo acquired by the image acquisition device is actually from the photo or video clip, o

Images