Action living body recognition method based on attitude estimation and action detection

Abstract

The invention discloses an action living body recognition method based on attitude estimation and action detection, and relates to the technical field of biological recognition. The method comprises the steps: recognizing a real person and an attack by enabling a user to cooperate to do an action, wherein an action instruction set is random, so whether the user is a living body or not can be judged more accurately; before a living body is made, in order to improve the one-time passing rate of a real person, carrying out the light recognition, face recognition in a circle, face alignment screenrecognition and face occlusion recognition on a user; estimating a depression angle, a deflection angle and a rotation angle of the user by adopting a posture estimation PSECNN model, and performinghead shaking, nodding and head raising recognition on the user, so as to accurately recognize the head action of the user; when blinking and mouth opening actions are identified, adopting an MCNN model and an ECNN model to replace mainstream detection based on feature points, so the blinking and mouth opening identification rate is ensured in precision; in vivo detection, action instructions are random, actions and action sequences need to be accurate, anti-copying recognition is carried out, and safety is higher.

Description

technical field [0001] The present invention relates to the technical field of biometric identification, in particular to a method for identifying a living body based on pose estimation and action detection. Background technique [0002] Liveness detection is to study how to distinguish whether the face captured by the current camera comes from a real living body (that is, a person) or an attack (including face photos, videos, masks, etc.). Face camouflage usually includes multiple methods. In the current business environment where face recognition is one of the important means of identification, this series of frauds will pose a potential threat to users of the face recognition identity system. Therefore, regardless of research and business The field has taken many measures on how to identify face camouflage attacks. Liveness detection is fundamentally a binary classification problem. To find the difference between live and non-living images, it mainly includes the followin...

AI Technical Summary

Problems solved by technology

[0013] (1) Without occlusion detection, for example, if the user wears a mask on the face, or the user wears sunglasses, or the user covers the mouth with his hand, etc., the recognition accuracy of opening the mouth and blinking will become worse at this time, and it is still done in a living body Finally, tell the user that the failure has occurred, and it cannot be discovered in advance, so it will be reminded in time

[0014] (2) The real-time user’s face is not aligned with the circle on the screen for recognition. As a result, the user’s face may not be in the camera during the process of doing it, and finally the action recognition fails because the face is not detected, or the action does not meet the specifications and fails.

[0015] (3) The recognition of blinking and opening the mou...

Images