An identity authentication method, device, electronic equipment and readable storage medium

Abstract

The application provides an identity authentication method, device, electronic equipment, and readable storage medium, wherein the identity authentication method includes: obtaining the identity information and user identification of the person to be authenticated; performing feature extraction on the face image to obtain the face feature vector, and extract the frequency spectrum features of the voice signal to obtain the voiceprint feature vector, which can obtain the face feature vector and voiceprint feature vector of the person to be authenticated; obtain the target face feature vector and target voiceprint feature vector corresponding to the user identification , and input the face feature vector, voiceprint feature vector, target face feature vector and target voiceprint feature vector into the pre-trained label determination model, the category label of the person to be authenticated can be obtained; if the category label is the first class label, it is determined that the person to be authenticated has passed the authentication. In this way, the identity information of the person to be authenticated can be effectively screened, the accuracy of identity authentication can be improved, and the security of identity authentication can be improved.

Description

technical field [0001] The present application relates to the technical field of biometric identification, in particular to an identity authentication method, device, electronic equipment and readable storage medium. Background technique [0002] In modern life, the comprehensive authentication system of face and voiceprint is particularly important to promote the security protection of data information. At present, in order to ensure the security of data, agencies, enterprises and institutions usually strictly control the approval operation from the personnel management process to ensure that personnel do not leak secrets during the operation process. From the data level, it is possible to ensure that operators do not disclose confidentiality during the use of data. [0003] At present, in the comprehensive authentication system of face and voiceprint, the comprehensive authentication is usually based on the similarity score after face recognition and the similarity score ...

AI Technical Summary

Problems solved by technology

[0003] At present, in the comprehensive authentication system of face and voiceprint, the comprehensive authentication is usually based on the similarity score after face recognition and the similarity score after voiceprint recognition. However, due to weak voiceprint features, The similarity threshold for voiceprint matching is low, resulting in non-real identity information being judged by the system, thus affecting the accuracy of identity authentication

Images