On the predictability in reversible steganography
On the predictability in reversible steganography
复制标题
DOI：
10.1007/s11235-022-00985-0
复制
发表时间：
2022-02
影响因子：
2.5
通讯作者：
Ching-Chun Chang;Xu Wang;Sisheng Chen;H. Kiya;I. Echizen
中科院分区：
文献类型：
--
作者：
Ching-Chun Chang;Xu Wang;Sisheng Chen;H. Kiya;I. Echizen
人工神经网络已经推进了可逆隐写术的前沿。神经网络的核心优势是能够对令人眼花缭乱的各种数据做出准确的预测。残差调制被公认为最先进的数字图像可逆隐写算法。该算法的核心是预测分析，即在给定某些像素相关信息的情况下对像素强度进行预测。这项任务可以被认为是一个低水平的视觉问题，因此可以部署用于解决类似类别问题的神经网络。在现有技术的基础上，本文研究了基于监督和非监督学习框架的像素强度的可预测性。可预测性分析支持自适应数据嵌入，这反过来又导致在容量和不可感知性之间更好地权衡。虽然传统方法通过局部图像模式的统计来估计可预测性，但基于学习的框架进一步考虑指定预测器可以做出正确预测的程度。不仅要考虑图像模式，而且要考虑使用中的预测器。实验结果表明，将基于学习的可预测性分析器引入到可逆隐写系统中，可以显著提高隐写性能。
Artificial neural networks have advanced the frontiers of reversible steganography. The core strength of neural networks is the ability to render accurate predictions for a bewildering variety of data. Residual modulation is recognised as the most advanced reversible steganographic algorithm for digital images. The pivot of this algorithm is predictive analytics in which pixel intensities are predicted given some pixel-wise contextual information. This task can be perceived as a low-level vision problem and hence neural networks for addressing a similar class of problems can be deployed. On top of the prior art, this paper investigates predictability of pixel intensities based on supervised and unsupervised learning frameworks. Predictability analysis enables adaptive data embedding, which in turn leads to a better trade-off between capacity and imperceptibility. While conventional methods estimate predictability by the statistics of local image patterns, learning-based frameworks consider further the degree to which correct predictions can be made by a designated predictor. Not only should the image patterns be taken into account but also the predictor in use. Experimental results show that steganographic performance can be significantly improved by incorporating the learning-based predictability analysers into a reversible steganographic system.