EFR-CSTP: Encryption for face recognition based on the chaos and semi-tensor product theory

Face recognition is a relatively common method humans use to confirm their identity. Protecting the safe transmission of face images has become a hot issue. This paper proposes an encryption method for face images, EFR-CSTP. The EFR-CSTP is very efficient because it only encrypts the facial in the face image. Firstly, the secret keys are generated by Hash. They are the parameters and the initial values of the two-dimensional logistic tent modular map (2D-LTMM), the chaotic sequence required for encryption by 2D-LTMM. Secondly, facial information is recognized by the histogram of oriented gradients (HOG). Note that the entire algorithm only encrypts this facial image. Finally, the facial image is used as the input of the EFR-CSTP, and the ciphertext image is generated by scrambling, STP combined with the XOR diffusion method. We evaluated our algorithm in the IMDB-WIKI dataset. We also evaluate the EFR-CSTP and other algorithms on the same datasets. The evaluation results show that the EFR-CSTP has excellent performance and efficiency.