Encrypted face feature matching method and device

Abstract

The invention relates to the technical field of data processing, in particular to an encrypted face feature matching method and device, and solves the problem that related personnel need to be recalled for feature recognition and an encrypted face feature library needs to be recreated when a face recognition algorithm is replaced under the condition that a face image is not stored, so that the recognition efficiency is improved. The method comprises the following steps: acquiring a first face feature of a to-be-recognized object, generating a feature encryption vector corresponding to the first face feature, then determining a conversion matrix between the feature encryption vector and each stored to-be-matched encryption vector, and matching the to-be-matched encryption vector with the to-be-matched encryption vector according to the conversion matrix. And calculating and screening out a to-be-matched encryption vector corresponding to the maximum vector dot product as a matched vector result. Therefore, on the basis of the vector dot product between the converted feature encryption vector and each stored to-be-matched encryption vector, the vector result matched with the to-be-recognized object in each stored to-be-matched encryption vector can be determined, and matching operation based on the encrypted face features is realized.

Description

technical field [0001] The present disclosure relates to the technical field of data processing, and in particular, to a method and device for matching encrypted facial features. Background technique [0002] With the continuous development of face recognition technology, there are more and more types of face recognition algorithms, and different face recognition algorithms are incompatible. [0003] At present, when most companies use a face recognition algorithm, they need to convene relevant personnel, and use the face recognition algorithm to extract the face features of the relevant personnel to form a face feature database. Subsequently, during face recognition, the acquired face features of the user to be identified are compared with the face features in the face feature database to determine the identity of the user to be identified. [0004] However, without storing face images to protect the privacy of the relevant personnel, when the enterprise wants to switch to...

AI Technical Summary

Problems solved by technology

[0005] Embodiments of the present disclosure provide a method and device for matching encrypted face features, which are used to solve the problem in the prior art that when the face recognition algorithm is replaced, relevant personnel need to be summoned to carry out the process. Feature recognition, recreating the encrypted face feature database, low work efficiency and time-consuming and laborious problems

Images