Study on an optical encryption algorithm based on compressive ghost imaging and super-resolution reconstruction

Optical encryption schemes based on compressive ghost imaging (CGI) are associated with low-quality decrypted images and unsatisfactory security. In order to cope with these issues, we propose an optical encryption algorithm based on compressive ghost imaging and super-resolution reconstruction. A convolution neural network is established to reconstruct the images. Compared with CGI, the convolutional neural network super-resolution convolutional neural networks can not only restore the reconstructed image of the CGI to a HR image, but also realize secondary encryption by using the convolution kernel parameter of the convolutional neural network. Therefore, this algorithm can improve the resolution of the decrypted image and the security of the algorithm. (paper)