Similar articles

Abstract: In the field of reversible data hiding (RDH), designing a high-precision predictor to reduce the embedding distortion and developing an effective embedding strategy to minimize the distortion caused by embedding information are the two most critical aspects. In this paper, we propose a new RDH method, including a predictor based on a transformer and a novel embedding strategy with multiple embedding rules. In the predictor part, we first design a transformer-based predictor. Then, we propose an image division method to divide the image into four parts, which can use more pixels as context. Compared with other predictors, the transformer-based predictor can extend the range of pixels for prediction from neighboring pixels to global ones, making it more accurate in reducing the embedding distortion. In the embedding strategy part, we first propose a complexity measurement with pixels in the target blocks. Then, we develop an improved prediction error ordering rule. Finally, we provide an embedding strategy including multiple embedding rules for the first time. The proposed RDH method can effectively reduce the distortion and provide satisfactory results in improving the visual quality of data-hidden images, and experimental results show that the performance of our RDH method is leading the field.

基于transformer和自适应嵌入策略的可逆信息隐藏

[1]Chen M, Chen ZY, Zeng X, et al., 2010. Model order selection in reversible image watermarking. IEEE J Sel Top Signal Process, 4(3):592-604.

[2]Chen M, Radford A, Child R, et al., 2020. Generative pretraining from pixels. Proc 37^th Int Conf on Machine Learning, Article 158.

[3]Coltuc D, 2011. Improved embedding for prediction-based reversible watermarking. IEEE Trans Inform Forens Secur, 6(3):873-882.

[4]Coltuc D, 2012. Low distortion transform for reversible watermarking. IEEE Trans Image Process, 21(1):412-417.

[5]Cox IJ, Miller ML, Bloom JA, 2002. Digital Watermarking. Morgan Kaufmann, San Francisco, USA.

[6]Dosovitskiy A, Beyer L, Kolesnikov A, et al., 2021. An image is worth 16×16 words: transformers for image recognition at scale. Proc Int Conf on Learning Representations.

[7]Dragoi IC, Caciula I, Coltuc D, 2018. Improved pairwise pixel-value-ordering for high-fidelity reversible data hiding. Proc 25^th IEEE Int Conf on Image Processing, p.1668-1672.

[8]Esser P, Rombach R, Ommer B, 2021. Taming transformers for high-resolution image synthesis. Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition, p.12873-12883.

[9]Goodfellow I, Pouget-Abadie J, Mirza M, et al., 2014. Generative adversarial nets. Proc 27^th Int Conf on Neural Information Processing Systems, p.2672-2680.

[10]He WG, Cai ZC, 2021. Reversible data hiding based on dual pairwise prediction-error expansion. IEEE Trans Image Process, 30:5045-5055.

[11]He WG, Cai J, Zhou K, et al., 2017. Efficient PVO-based reversible data hiding using multistage blocking and prediction accuracy matrix. J Vis Commun Image Represent, 46:58-69.

[12]Hong W, 2012. Adaptive reversible data hiding method based on error energy control and histogram shifting. Opt Commun, 285(2):101-108.

[13]Howard PG, Vitter JS, 2016. Arithmetic coding for data compression. In: Kao MY (Ed.), Encyclopedia of Algorithms. Springer, New York, USA, p.145-150.

[14]Hu RW, Xiang SJ, 2021. CNN prediction based reversible data hiding. IEEE Signal Process Lett, 28:464-468.

[15]Hu RW, Xiang SJ, 2022. Reversible data hiding by using CNN prediction and adaptive embedding. IEEE Trans Patt Anal Mach Intell, 44(12):10196-10208.

[16]Jafar IF, Darabkh KA, Al-Zubi RT, et al., 2016. Efficient reversible data hiding using multiple predictors. Comput J, 59(3):423-438.

[17]Karras T, Aila T, Laine S, et al., 2018. Progressive growing of GANs for improved quality, stability, and variation. Proc 6^th Int Conf on Learning Representations.

[18]Karras T, Laine S, Aila T, 2019. A style-based generator architecture for generative adversarial networks. Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition, p.4401-4410.

[19]Li XL, Yang B, Zeng TY, 2011. Efficient reversible water- marking based on adaptive prediction error expansion and pixel selection. IEEE Trans Image Process, 20(12):3524-3533.

[20]Li XL, Li J, Li B, et al., 2013. High-fidelity reversible data hiding scheme based on pixel-value-ordering and prediction error expansion. Signal Process, 93(1):198-205.

[21]Liu ZW, Luo P, Wang XG, et al., 2015. Deep learning face attributes in the wild. Proc IEEE Int Conf on Computer Vision, p.3730-3738.

[22]Luo LX, Chen ZY, Chen M, et al., 2010. Reversible image watermarking using interpolation technique. IEEE Trans Inform Forens Secur, 5(1):187-193.

[23]Ou B, Li XL, Zhao Y, et al., 2013. Pairwise prediction error expansion for efficient reversible data hiding. IEEE Trans Image Process, 22(12):5010-5021.

[24]Ou B, Li XL, Zhao Y, et al., 2014. Reversible data hiding using invariant pixel-value-ordering and prediction error expansion. Signal Process Image Commun, 29(7):760-772.

[25]Ou B, Li XL, Wang JW, 2016. High-fidelity reversible data hiding based on pixel-value-ordering and pairwise prediction error expansion. J Vis Commun Image Represent, 39:12-23.

[26]Peng F, Li XL, Yang B, 2014. Improved PVO-based reversible data hiding. Dig Signal Process, 25:255-265.

[27]Qu XC, Kim HJ, 2015. Pixel-based pixel value ordering predictor for high-fidelity reversible data hiding. Signal Process, 111:249-260.

[28]Russakovsky O, Deng J, Su H, et al., 2015. ImageNet large scale visual recognition challenge. Int J Comput Vis, 115(3):211-252.

[29]Sachnev V, Kim HJ, Nam J, et al., 2009. Reversible watermarking algorithm using sorting and prediction. IEEE Trans Circ Syst Video Technol, 19(7):989-999.

[30]Thodi DM, Rodriguez JJ, 2007. Expansion embedding techniques for reversible watermarking. IEEE Trans Image Process, 16(3):721-730.

[31]Tian J, 2003. Reversible data embedding using a difference expansion. IEEE Trans Circ Syst Video Technol, 13(8):890-896.

[32]van den Oord A, Vinyals O, Kavukcuoglu K, 2017. Neural discrete representation learning. Proc 31^st Int Conf on Neural Information Processing Systems, p.6309-6318.

[33]Vaswani A, Shazeer N, Parmar N, et al., 2017. Attention is all you need. Proc 31^st Int Conf on Neural Information Processing Systems, p.6000-6010.

[34]Wang X, Ding J, Pei QQ, 2015. A novel reversible image data hiding scheme based on pixel value ordering and dynamic pixel block partition. Inform Sci, 310:16-35.

[35]Wang XY, Wang XY, Ma B, et al., 2021. High precision error prediction algorithm based on ridge regression predictor for reversible data hiding. IEEE Signal Process Lett, 28:1125-1129.

[36]Weng SW, Zhang GH, Pan JS, et al., 2017. Optimal PPVO-based reversible data hiding. J Vis Commun Image Represent, 48:317-328.

[37]Weng SW, Shi YQ, Hong W, et al., 2019. Dynamic improved pixel value ordering reversible data hiding. Inform Sci, 489:136-154.

[38]Zhang T, Li XL, Qi WF, et al., 2020a. Location-based PVO and adaptive pairwise modification for efficient reversible data hiding. IEEE Trans Inform Forens Secur, 15:2306-2319.

[39]Zhang T, Li XL, Qi WF, et al., 2020b. Prediction error value ordering for high-fidelity reversible data hiding. Proc 26^th Int Conf on Multimedia Modeling, p.317-328.

[40]Zheng CX, Cham TJ, Cai JF, et al., 2022. Bridging global context interactions for high-fidelity image completion. Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition, p.11512-11522.

[41]Zhou BL, Lapedriza A, Khosla A, et al., 2018. Places: a 10 million image database for scene recognition. IEEE Trans Patt Anal Mach Intell, 40(6):1452-1464.