Based on discrete Fourier transforms and logistic-exponent-sine map, this paper investigates an encryption algorithm for multiple color images. In the encryption process, each color image represented in trinion matrix is performed by block-wise discrete trinion Fourier transforms. Then the first real matrix is constructed by splicing real and imaginary parts of transformed results. Followed by two-dimensional discrete Fourier transform, the second real matrix is synthesized only using half of the spectrum on the basis of the conjugate symmetry property. In order to further enhance the randomness of interim result, the random multi-resolution singular value decomposition is exploited. Afterwards, a sharing process is utilized to get final cipherimages. Numerical simulations performed on 300 color images have shown that quality of correctly decrypted images is much better, where the PSNR value is up to 305.03 dB. The number of changing pixel rate and unified average changing intensity are respectively greater than 99.99% and 33.33%, indicating good sensitivity. The comparison with other methods under noise and cropping attacks validates the reliability of the proposed algorithm.

基于离散傅里叶变换和逻辑指数正弦图，本文研究了多彩色图像的加密算法。在加密过程中，通过块状离散的Trinion傅里叶变换来执行Trinion矩阵中表示的每个彩色图像。然后，通过拼接转换结果的实部和虚部构造第一个实数矩阵。其次是二维离散傅里叶变换，根据共轭对称性，仅使用频谱的一半来合成第二实矩阵。为了进一步提高中间结果的随机性，采用了随机多分辨率奇异值分解方法。之后，利用共享过程来获得最终的密文。对300幅彩色图像进行的数值模拟表明，正确解密的图像的质量要好得多，其中PSNR值高达305.03 dB。像素变化率和统一平均变化强度的个数分别大于99.99％和33.33％，表明灵敏度良好。与其他方法在噪声和裁剪攻击下的比较验证了所提算法的可靠性。