基于混沌卷积的光学图像分块加密方法

Optical Image Block Encryption Method Based on Chaotic Convolution

基于分块压缩感知理论和随机卷积理论,提出了一种基于混沌卷积的光学图像分块加密方法。首先将图像分为大小相同的分块子图像,针对每个子图像,利用级联混沌系统生成混沌相位模板和混沌振幅模板,将子图像与混沌相位模板进行混沌卷积;然后利用混沌振幅模板进行混沌下采样,获得加密压缩后的分块图像;最后将各分块加密图像复原为最终的加密图像。该方法每个分块子图像具有不同的加密密钥,以提高算法的安全性,混沌卷积过程中采用分数傅里叶变换替代傅里叶变换,以增大密钥空间。对加密方法的抗噪声攻击性、抗裁剪攻击性、统计特性、密钥敏感性等进行仿真实验,结果表明了该方法的可行性和安全性。

Based on block compressed sensing theory and random convolution theory,a new optical image block encryption method based on chaotic convolution is proposed.First,blocks of the same size are created from the plain image.A chaotic phase mask and a chaotic amplitude mask are generated for each block by a cascaded chaotic system,which is then used to convolute the block with the chaotic phase mask,and chaotic subsampling is followed using a chaotic amplitude mask to obtain the encrypted and compressed block image.Finally,all encrypted blocks are restored to the final encrypted image.Note that each block has a different key to increase the security,and fractional Fourier transform is used instead of Fourier transform in the process of chaotic convolution to increase the key space.Simulation is conducted on statistical analysis,noise attack resistance test,cropping attack resistance test,and key sensitivity test.The viability and security of the suggested encryption system are shown by numerical results.