Joint compressive autoencoders for full-image-to-image hiding
conference contributionposted on 2021-05-17, 13:41 authored by Xiyao Liu, Ziping Ma, Xingbei Guo, Jialu Hou, Lei Wang, Jian Zhang, Gerald SchaeferGerald Schaefer, Hui FangHui Fang
Image hiding has received significant attentions due to the need of enhanced multimedia services, such as multimedia security and meta-information embedding for multimedia augmentation. Recently, deep learning-based methods have been introduced that are capable of significantly increasing the hidden capacity and supporting full size image hiding. However, these methods suffer from the necessity to balance the errors of the modified cover image and the recovered hidden image. In this paper, we propose a novel joint compressive autoencoder (J-CAE) framework to design an image hiding algorithm that achieves full-size image hidden capacity with small reconstruction errors of the hidden image. More importantly, it addresses the trade-off problem of previous deep learning-based methods by mapping the image representations in the latent spaces of the joint CAE models. Thus, both visual quality of the container image and recovery quality of the hidden image can be simultaneously improved. Extensive experimental results demonstrate that our proposed framework outperforms several state-of-the-art deep learning-based image hiding methods in terms of imperceptibility and recovery quality of the hidden images while maintaining full-size image hidden capacity.
National Natural Science Foundation of China (61602527)
Natural Science Foundation of Hunan Province, China (2020JJ4746, 2017JJ3416, 2018JJ2548)
Mobile Health Ministry of Education-China Mobile Joint Laboratory
- Computer Science
Published in2020 25th International Conference on Pattern Recognition (ICPR)
Pages7743 - 7750
Source25th International Conference on Pattern Recognition (ICPR 2020)
- AM (Accepted Manuscript)
Rights holder© IEEE
Publisher statement© 20XX IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.