Biological characteristic processing method and device

Abstract

The invention discloses a biological feature processing method and device. The method comprises the following steps: partitioning a biological feature vector of a biological feature to obtain a plurality of sub-feature vectors; allocating a symbol transformation parameter value and a basic disturbance parameter value to each sub-feature vector; determining an amplitude transformation parameter value of the single sub-feature vector based on the maximum disturbance value L, the disturbance resolution M and the basic disturbance parameter value of the single sub-feature vector; based on the single sub-feature vector, and the symbol transformation parameter value and the amplitude transformation parameter value corresponding to the single sub-feature vector, performing direction transformation and amplitude transformation on the single sub-feature vector to obtain a post-disturbance vector of the single sub-feature vector; and determining a post-disturbance vector of the biological feature vector based on the post-disturbance vectors of all the sub-feature vectors. According to the process, disturbance is added in the biological feature vector, even if an attacker obtains the feature, the to-be-compared feature cannot be determined, and privacy leakage is avoided.

Description

technical field [0001] The present invention relates to the technical field of data processing, in particular to a biometric processing method and device. Background technique [0002] For the biometric feature recognition system, feature recognition is usually performed based on the feature vector by extracting the feature vector in the image or audio to be recognized. [0003] Taking the face image feature recognition system as an example, the feature extractor is usually used to map the face image to be compared to the face feature vector. In the process of feature recognition, the face feature vector is also compared with the corresponding feature vector Therefore, it is judged whether the face feature vector and the corresponding feature vector are from the same person. [0004] Although the face feature vector is a vector rather than the original picture, the face picture to be compared can be easily restored from the face feature vector, resulting in privacy leakage....

AI Technical Summary

Problems solved by technology

[0005] In view of this, the present invention provides a biometric processing method and device to solve the problem in the prior art. Although the face feature vector is a vector rather than the original picture, from the face feature vector, it can be easily Restore the face picture to be compared, leading to the problem of privacy leakage

Images