针对图像无载体信息隐藏算法嵌入容量与鲁棒性无法很好兼顾的问题，提出了一种基于纹理特征分类与合成的鲁棒无载体信息隐藏算法，使用空间金字塔算法提取纹理图像特征，通过监督式分类训练得到分类模型，同一类别下的不同图像块，利用位置信息进行区分，根据图像块分类和位置信息的不同构建映射字典，传递秘密信息；发送方依据秘密信息选择图像块并根据公共密钥将所有图像块组合为一幅大尺寸图像，通过可逆形变生成复杂的纹理图像并发送给接收方；接收方根据密钥将纹理图像恢复为图像块，利用分类模型识别图像块所属分类并确定位置信息，对照映射字典提取秘密信息.实验和分析表明该算法对JPEG压缩、高斯噪声、椒盐噪声等攻击具有较好的鲁棒性，同时嵌入容量可随图像类别的增加得到提高.
Aiming at the problem that the embedding rate and robustness of coverless information hiding cannot be well balanced, a robust coverless information hiding scheme based on texture feature classification and synthesis is proposed. In this scheme, texture image features are extracted with spatial pyramid algorithm, and classification models are obtained by supervised classification training. A mapping dictionary is constructed according to the classification of image blocks and different location information. The sender chooses image blocks based on secret information and combines all image blocks into one image according to public key, then generates complex lines through reversible deformation. The texture image can be restored to image blocks by using the key, and the classification model is used to identify the classification of image blocks and determine the location information. Finally, secret information is extracted based on the mapping dictionary. Experimental results show that the proposed scheme has strong robustness against JPEG compression, Gaussian noise, salt and pepper noise and other typical attacks, and the embedding capacity can be further improved with the increase of image category number.
[1] 张新鹏,钱振兴,李晟.信息隐藏研究展望[J].应用科学学报,2016, 34(5):475-489. Zhang X P, Qian Z X, Li S. Prospect of digital steganography research[J]. Journal of Applied Sciences, 2016, 34(5):475-489.(in Chinese)
[2] 周志立,曹燚,孙星明.基于图像Bag-of-Words模型的无载体信息隐藏[J].应用科学学报,2016, 34(5):527-536. Zhou Z L, Cao Y, Sun X M. Coverless information hiding based on bag-of-words model of image[J]. Journal of Applied Sciences, 2016, 34(5):527-536.(in Chinese)
[3] Zhang X, Peng F, Long M. Robust coverless image steganography based on DCT and LDA topic classification[J]. IEEE Transactions on Multimedia, 2018,(99):1-1.
[4] Fridruch J. Steganography in digital media:principles, algorithms, and applications[M]. Cambridge, UK:Cambridge University Press, 2010.
[5] Lowe D G. Distinctive image features from scale-invariant key-points[J]. International Journal of Computer Vision, 2004, 60(2):91-110.
[6] Zhou Z L, Sun H, Harint R. Coverless image steganography without embedding[C]//International Conference on Cloud Computing and Security, Nanjing, China, 2015:123-132.
[7] Yuan C S, Xia Z H, Sun X M. Coverless image steganography based on SIFT and BOF[J]. Journal of Internet Technology, 2017, 18:435-442.
[8] Otori H, Kuriyama S. Data-embeddable texture synthesis[C]//Proceedings of the 8th International Symposium on Smart Graphics, Kyoto, Japan, 2007:146-157.
[9] Otori H, Kuriyama S. Texture synthesis for mobile data communications[J]. IEEE Conference Graphics Applications, 2009, 29(6):74-81.
[10] Lu S, Jaffer A, Jin X, et al. Mathematical marbling[J]. IEEE Computer Graphics and Applications, 2012, 32(6):26-35.
[11] Xu J, Mao X, Jin X. Nondissipative marbling[J]. IEEE Computer Graphics and Applications, 2008, 28(2):35-43.
[12] Xu J, Mao X, Jin X. Hidden message in a deformation-based texture[J]. Visual Computer, 2015, 31(12):1653-1699.
[13] 潘琳,钱振兴,张新鹏.基于构造纹理图像的数字隐写[J].应用科学学报,2016, 34(5):625-632. Pan L, Qian Z X, Zhang X P. Steganography by constructing texture images[J]. Journal of Applied Sciences, 2016, 34(5):625-632.(in Chinese)
[14] Qin C, Chang C C, Tsou P L. Dictionary-based data hiding using image hashing strategy[J]. International Journal of Innovative Computing Information & Control, 2013, 9(2):599-610.
[15] Lazebnik S, Schmid C, Ponce J. Beyond bags of features:spatial pyramid matching for recognizing natural scene categories[C]//IEEE Computer Society Conference on Computer Vision and Pattern Recognition, New York, USA, 2006:2169-2178.
[16] 章鸣嬛,陈瑛,沈瑛,等.人工神经网络和支持向量机性能比较及其在DMD疾病识别中的应用[J].上海理工大学学报,2016, 38(4):346-351. Zhang M H, Chen Y, Shen Y, et al. Comparative study on the performances of ANN and SVM and their application in the identification of DMD disease[J]. Journal of University of Shanghai for Science and Technology, 2016, 38(4):346-351.(in Chinese)
[17] 孙佳忆,曹芳,唐振军,等.基于图像拼接的可信图像修补方法[J].上海理工大学学报,2018, 40(2):150-157. Sun J Y, Cao F, Tang Z J, et al. Trustable image in-painting method based on image mosaics[J]. Journal of University of Shanghai for Science and Technology, 2018, 40(2):150-157.(in Chinese)
[18] 唐银凤,黄志明,黄荣娟,等.基于多特征提取和SVM分类器的纹理图像分类[J].计算机应用与软件,2011, 28(6):22-25. Tang Y F, Huang Z M, Huang R J, et al. Texture image classification based on multi-feature extraction and SVM classifier[J]. Computer Application and Software, 2011, 28(6):22-25.(in Chinese)
[19] Yang J, Jiang Y G, Hauptmann A G. Evaluating bag-of-visual-words representations in scene classification[C]//Proceedings of the 9th ACM SIGMM International Workshop on Multimedia Information Retrieval, MIR 2007, Bavaria, Germany, ACM, 2007:197-206.
