A data hiding scheme based on U-Net and wavelet transform

摘要

As deep learning was used in the field of data hiding, the capacity of data hiding had been greatly increased. In addition, the wavelet transform in the traditional data hiding technology performed well, and the hidden image was invisible compared with the spatial domain scheme A data hiding scheme based on U-Net and wavelet transform was proposed in this paper, which innovatively combined the advantages of U-Net in image detail feature processing and the ability of wavelet transform to divide image details. Data hiding and extraction were realized through the jointly trained hidden network and extraction network respectively. The wavelet coefficients of the secret data were hidden in the image through the hidden network, and a hidden image with good visual effects could be obtained. The image feature was subdivided into four wavelet coefficients in the extraction network, and finally the secret data image was obtained through inverse wavelet transform. The experimental results shown that the proposed scheme had better hidden data invisibility than the traditional scheme, and the data extraction was more accurate.