引文简译New CNN-based Predictor For Reversible Data Hiding

New CNN-based Predictor For Reversible Data Hiding

引文

简述可逆信息隐藏

可逆信息隐藏(Reversible data hiding,RDH)是一种能将信息隐藏在数字媒体中，并且能够保证提取出信息之后能无损恢复数字媒体的技术。

数字媒体包括：

1.音频

2.图片

3.视频

可逆信息隐藏具体可分为几种类型：

1.Lossless compression[2]

2.Difference expansion(DE)[3]

3.Histogram shifting(HS)[4]

4.Prediction-error expansion(PEE)[5]-[9]

由于本文创新算法属于PEE算法，下面介绍一些PEE算法的研究情况。

PEE研究内容的简介

PEE算法可以分两个步骤：

1.Prediction stage

对图像作出准确的预测，改进目标是让预测更准确。

2.Embedding stage

修改获得的预测误差直方图(prediction error histogram)，以此嵌入秘密信息。

两个改进方向以下会介绍。

本文的创新在Prediction stage中。

1.Prediction stage

传统方法：

多使用临近像素来进行预测

方法有：

Difference predictor(DP)[3]

Median edge direction predictor(MEDP)[5]

Rhombus predictor(RP)[6]

Gradient adaptive predictor(GAP)[7]

Partial differential equation predictor(PDEP)[8]

Multi-predictor[9]

传统方法，由于locality和linearity的限制(limitations)，减小预测误差(prediction-error)的能力有瓶颈。

预测误差：像素的预测值与实际值之间的误差(原文：The difference between the predicted value and the to-be-predicted value)。

于是，研究者在深度学习崛起，图像分类、目标识别等领域取得重大突破的背景下，改用CNN，力图实现预测性能的提升。

CNN方法：

研究近况：

Luo等人[10]：

提出了一个基于CNN的立体图像可逆信息隐藏方法。(Proposed a stereo image RDH method based on the CNN.)

Hu等人[11]：

提出了一个应用于灰度图像的CNN预测器。(Proposed a new CNN-based predictor(CNNP) for the grayscale images.)

上作的作者们还提出，由于CNN有多个感受域[12]，还能够进行全局优化，它在信息隐藏中还有更大的施展空间。(The authors claimed that since the CNN has the abilities of multi receptive fields[12] and global optimization, it can make more room for data hiding.)

Hu等人[13]：

改善了[11]中的图像划分策略，提出了一个性能更好的CNN预测器(CNN-based predictor,CNNP)。

2.Embedding stage

重复一下这个阶段的工作，那就是研究新方法来修改获得的预测误差直方图。(The researchers focus on designing some new rules to modify the obtained prediction error histogram.) 

两种方法：

1.生成有效的直方图映射关系(Construct efficient reversible histogram mappping)

一维映射方法[4]-[9]（其中[6]的阶段方法被本文采用，以此结合成完整的RDH算法）

高维映射方法[14]-[16]

2.改善、发明新效的嵌入策略(embedding strategy)[17]

原理：

新的嵌入策略会选择嵌入效率更高(high embedding efficiency)的像素

本文工作内容的简介

第一阶段Prediction stage两处创新

1.采用更多临近像素来预测待测像素的预处理

在把图像放入CNN网络之前，先基于每个像素临近的8个像素生成预处理图片，这样的图片放入CNN预测器中会提升预测效果。

2.新的CNN预测器

设计了一个更好的CNN网络来预测前面预处理过的图片。经由这个网络，生成的图片预测准确率更高。

第二阶段Embedding stage工作

结合经典的PEE嵌入策略[6]，本文的工作构成了一个完整的RDH算法。

实验结果

实验取得了满意的结果，最终生成的载密图片的视觉质量，比起现有的RDH算法，得到了提升。

[1] Y. -Q. Shi, X. Li, X. Zhang, H.-T. Wu, and B. Ma, “Reversible data hiding: Advances in the past two decades,” IEEE Access, vol. 4, pp. 3210–3237, 2016.

[2] M. U. Celik, G. Sharma, A. M. Tekalp and E. Saber, “Lossless generalized-LSB data embedding,” IEEE Transactions on Image Processing, vol. 14, no. 2, pp. 253-266, Feb. 2005.

[3] J. Tian, “Reversible data embedding using a difference expansion,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 13, no. 8, pp. 890-896, Aug. 2003.

[4] Z. Ni, Y. -Q. Shi, N. Ansari and W. Su, “Reversible data hiding,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 16, no. 3, pp. 354-362, March 2006.

[5] D. M. Thodi and J. J. Rodriguez, “Expansion Embedding Techniques for Reversible Watermarking,” IEEE Transactions on Image Processing, vol. 16, no. 3, pp. 721-730, March 2007.

[6] V. Sachnev, H. J. Kim, J. Nam, S. Suresh and Y.Q. Shi, “Reversible Watermarking Algorithm Using Sorting and Prediction,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 19, no. 7, pp. 989-999, July 2009.

[7] D. Coltuc, “Low distortion transform for reversible watermarking,” IEEE Transactions on Image Processing, vol. 21, no. 1, pp. 412-417, Jan. 2012.

[8] B. Ou, X. Li, Y. Zhao and R. Ni, “Reversible data hiding based on PDE predictor,” Journal of Systems and Software, vol. 86, no. 10, pp. 2700-2709, 2013.

[9] I. F. Jafar, K. A. Darabkh, R. T. Al-Zubi and R. A. Al Na’mneh, “Efficient Reversible Data Hiding Using Multiple Predictors,” The Computer Journal, vol. 59, no. 3, pp. 423-438, March 2016.

[10] T. Luo, G. Jiang, M. Yu, C. Zhong, H. Xu, and Z. Pan, “Convolutional neural networks-based stereo image reversible data hiding method,” Journal of Visual Communication and Image Representation, vol. 61, pp. 61-73, 2019.

[11] R. Hu and S. Xiang, “CNN Prediction Based Reversible Data Hiding,” IEEE Signal Processing Letters, vol. 28, pp. 464-468, 2021.

[12] W. Luo, Y. Li, R. Urtasun, and R. Zemel, “Understanding the effective receptive field in deep convolutional neural networks,” Adv. Neural Inf. Process. Syst., vol. 29, pp. 4898–4906, 2016.

[13] R. Hu and S. Xiang, “Reversible Data Hiding by Using CNN Prediction and Adaptive Embedding,” IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 1-1.

[14] B. Ou, X. Li, Y. Zhao, R. Ni and Y. -Q. Shi, “Pairwise Prediction-Error Expansion for Efficient Reversible Data Hiding,” IEEE Transactions on Image Processing, vol. 22, no. 12, pp. 5010-5021, Dec. 2013.

[15] H. Wu, X. Cao, R. Jia and Y. Cheung, “Reversible Data Hiding with Brightness Preserving Contrast Enhancement by Two-dimensional Histogram Modification,” IEEE Transactions on Circuits and Systems for Video Technology, vol 32, no. 11, pp. 7605 - 7617, 2022.

[16] Q. Chang, X. Li and Y. Zhao, “Reversible Data Hiding for Color Images Based on Adaptive Three-Dimensional Histogram Modification,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 32, no. 9, pp. 5725-5735, Sept. 2022

[17] W. He, G. Xiong and Y. Wang, “Reversible Data Hiding Based on Adaptive Multiple Histograms Modification,” IEEE Transactions on Information Forensics and Security, vol. 16, pp. 3000-3012, 2021.

[18] S. Ioffe and C. Szegedy, “Batch normalization: Accelerating deep network training by reducing internal covariate shift,” Proc. Int. Conf. Mach. Learn., 2015, pp. 448–456.

[19] J. Deng, W. Dong, R. Socher, L. -J. Li, Kai Li and Li Fei-Fei, “ImageNet: A large-scale hierarchical image database,” 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248-255, 2009.

[20] Y. Lecun, L. Bottou, Y. Bengio and P. Haffner, “Gradient-based learning applied to document recognition,” Proceedings of the IEEE, vol. 86, no. 11, pp. 2278-2324, Nov. 1998.

[21] D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” 2014, arXiv:1412.6980.

[22] G. Schaefer and M. Stich. “UCID: An uncompressed color image database,” Storage and Retrieval Methods and Applications for Multimedia 2004, vol. 5307, pp. 472-480, 2003.

[23] R. Franzen, “Kodak lossless true color image suite,” Website: http://r0k.us/graphics/kodak, 1999.