基于SVD和DCNN的彩色图像多功能零水印算法

doi:10.6040/j.issn.1672-3961.0.2017.408

山东大学学报(工学版) ›› 2018, Vol. 48 ›› Issue (3): 25-33.doi: 10.6040/j.issn.1672-3961.0.2017.408

基于SVD和DCNN的彩色图像多功能零水印算法

赵彦霞^1,2, 王熙照^1,3*

1. 河北大学管理学院, 河北保定 071002;2. 河北经贸大学信息技术学院, 河北石家庄 050061;3. 深圳大学计算机与软件学院, 广东深圳 518060

收稿日期:2017-05-17 出版日期:2018-06-20 发布日期:2017-05-17
通讯作者: 王熙照(1963— ),男,教授,博士,主要研究方向为机器学习,模式识别. E-mail:xizhaowang@ieee.org E-mail:zyxa6@126.com
作者简介:赵彦霞(1970— ),女,讲师,博士研究生,主要研究方向为不确定知识管理和机器学习,数字水印,信息处理等. E-mail:zyxa6@126.com
基金资助:
国家自然科学基金资助项目(71371063,61672205);河北省应用基础研究计划重点基础研究资助项目(16960314D);河北省科技计划资助项目(15454704D);河北省人力资源社会保障科研合作课题资助项目(JRSHZ-2016-07038);深圳市科技计划资助项目(JCYJ20150324140036825)

Multipurpose zero watermarking algorithm for color image based on SVD and DCNN

ZHAO Yanxia^1,2, WANG Xizhao^1,3*

1. College of Management, Hebei University, Baoding 071002, Hebei, China;
2. College of Information &
Technology, Hebei University of Economics and Business, Shijiazhuang 050061, Hebei, China;
3. College of Computer Science &
Software Engineering, Shenzhen University, Shenzhen 518060, Guangdong, China

Received:2017-05-17 Online:2018-06-20 Published:2017-05-17

摘要/Abstract

摘要： 为了对彩色图像进行版权保护和篡改定位,提出一种基于奇异值分解(singular value decomposition, SVD)和深度卷积神经网络(deep convolutional neural network, DCNN)的彩色图像多功能零水印算法。将原始RGB彩色图像转换成YCbCr彩色图像,对原始图像的Y、Cb、Cr通道离散小波变换得到的系数矩阵进行奇异值分解,得到DCNN的输入矩阵,从DCNN输出层的输入矩阵中获取原始图像信息矩阵,生成零鲁棒水印图像。从Y通道小波变换得到的低频子带系数矩阵中获取原始图像信息矩阵,生成零半脆弱水印图像。试验结果证明,提出的算法不但有效,而且对强度较大的常见攻击有较好的抵抗能力。

关键词: 版权保护, 篡改定位, 深度卷积神经网络, 多功能零水印, 奇异值分解, 离散小波变换

Abstract: A multipurpose zero watermarking algorithm for color image based on SVD(singular value decomposition)and DCNN(deep convolutional neural network)were proposed for the copyright protection and tamper location of color image. The original RGB color image was transformed into YCbCr color image. The Y channel, Cb channel and Cr channel were transformed by DWT(discrete wavelet transform), some matrices were got through decomposing the coefficient matrices by SVD and got the inputs matrices of DCNN. The information matrix of original image was got from the inputs matrix of output layer of DCNN and was used to generate zero robust watermarking image. The information matrix was got from the coefficient matrix of low frequency subband through the DWT of Y channel and was used to generate the zero semi-fragile watermarking image. The experimental results showed that the algorithm was not only efficient but also had good resistance to the strong common attacks.

Key words: tamper location, singular value decomposition, multipurpose zero watermarking, discrete wavelet transform, copyright protection, deep convolutional neural network

中图分类号:

TP391

赵彦霞, 王熙照. 基于SVD和DCNN的彩色图像多功能零水印算法[J]. 山东大学学报(工学版), 2018, 48(3): 25-33.

ZHAO Yanxia, WANG Xizhao. Multipurpose zero watermarking algorithm for color image based on SVD and DCNN[J]. JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE), 2018, 48(3): 25-33.

参考文献

[1] TIRKEL A Z, RANKIN G A, SCHYNDEL R G, et al. Electronic watermark[C] //Digital Image Computing, Technology and Applications(DICTA), 1993. Sidney, Australia: Australian Pattern Recognition Society, 1993: 666-673.
[2] 孙圣和,陆哲明,牛夏牧,等. 数字水印技术及应用[M]. 北京: 科学出版社, 2004.
[3] AMIT M, NEELESH M. Adaptive lossless medical image watermarking algorithm based on DCT & DWT[J]. Procedia Computer Science, 2016, 78:88-94.
[4] 张君捧,张庆范,杨红娟.基于块特征和混沌序列的图像篡改检测与恢复[J]. 山东大学学报(工学版),2014,44(6):63-69. ZHANG Junpeng, ZHANG Qingfan, YANG Hongjuan. Images tamper detection and recovery based on block features and chaotic sequence[J]. Journal of Shandong University(Engineering Science), 2014, 44(6):63-69.
[5] 王向阳, 杨红颖, 牛盼盼,等. 基于四元数指数矩的鲁棒彩色图像水印算法[J]. 计算机研究与发展,2016,53(3):651-665. WANG Xiangyang, YANG Hongying, NIU Panpan, et al. Quaternion exponent moments based robust color image watermarking[J]. Journal of Computer Research and Development, 2016, 53(3):651-665.
[6] NGUYEN T S, CHANG C C, YANG X Q. A reversible image authentication scheme based on fragile watermarking in discrete wavelet transform domain[J]. International Journal of Electronics and Communications(AEU), 2016, 70(8):1055-1061.
[7] AMINI M, AHMAD M O, SWAMY M N S. Digital watermark extraction in wavelet domain using hidden Markov model[J]. Multimedia Tools and Applications, 2017, 76(3):3731-3749.
[8] 温泉, 孙锬锋, 王树勋. 零水印的概念与应用[J]. 电子学报, 2003, 31(2): 214-216. WEN Quan, SUN Tanfeng, WANG Shuxun. Concept and application of zero-watermark[J]. Acta Electronica Sinica, 2003, 31(2): 214-216.
[9] ZHOU Z Y. Digital video zero-watermarking algorithm based on contourlet transform[J]. Microcomputer Information, 2010, 26(35):82-84.
[10] CHEN X S, BU G L, LI H T, et al. A video zero-watermark algorithm based on the contourlet transform[C] //The 3rd International Conference on Multimedia Technology(ICMT), 2013. Paris, France: Atlantis Press, 2013:216-223.
[11] CAI Y M, GUO W Q, DING H Y. An audio blind watermarking scheme based on DWT-SVD[J]. Journal of Software, 2013, 8(7):1801-1808.
[12] LEI M, YANG Y, LIU X M, et al. Audio zero-watermark scheme based on discrete cosine transform-discrete wavelet transform-singular value decomposition[J]. China Communications, 2016, 13(7):117-121.
[13] ZHU P, XIANG G L, SONG W N, et al. A text zero-watermarking algorithm based on Chinese phonetic alphabets[J]. Wuhan University Journal of Natural Sciences, 2016, 21(4): 277-282.
[14] JALIL Z, MIRZA A M, SABIR M. Content based zero-watermarking algorithm for authentication of text documents[J]. International Journal of Computer Science and Information Security, 2010,7(2):248-255.
[15] KIM H D. CRT-based color image zero-watermarking on the DCT domain[J]. International Journal of Contents, 2015, 11(3):39-46.
[16] SINGH A, RAGHUVANSHI N, DUTTA M K, et al. An SVD based zero watermarking scheme for authentication of medical images for tele-medicine applications[C] //The 39th International Conference on Telecommunications and Signal Processing(TSP), 2016.Vienna, Austria: IEEE, 2016:511-514.
[17] LE H D, XU X Y, WANG Q, et al. Zero-watermarking for face image protection in database[J]. Journal of Internet Technology, 2016, 17(1):129-135.
[18] VELLAISAMY S, RAMESH V. Inversion attack resilient zero-watermarking scheme for medical image authentication[J]. IET Image Processing, 2014,8(12):718-727.
[19] HAN B R, LI J B, LI Y J. Zero-watermarking algorithm for medical volume data based on difference hashing[J]. International Journal of Computers Communications & Control, 2015,10(2): 188-199.
[20] LI D, LIU Z, CUI L H. A zero-watermark scheme for identification photos based on QR code and visual cryptography[J]. International Journal of Security and Its Applications, 2016, 10(1): 203-214.
[21] 倪顾伟. 基于神经网络的数字水印算法的研究与实现[D]. 南京: 南京理工大学, 2012. NI Guwei. Research and implementation of digital watermarking algorithm based on neural network[D]. Nanjing: Nanjing University of Science and Technology, 2012.
[22] 王雯霞. 一种基于奇异值分解的图像零水印新算法[J]. 计算机时代, 2010(4): 8-10. WANG Wenxia. A new image zero-watermarking algorithm based on SVD[J]. Computer Era, 2010(4): 8-10.
[23] 肖振久, 李南, 王永滨,等. 基于超混沌的医学图像篡改定位零水印算法[J]. 计算机工程与应用, 2017,53(7):115-120. XIAO Zhenjiu, LI Nan, WANG Yongbin, et al. Zero watermarking scheme for medical image temper location based on hyper-chaos encryption[J]. Computer Engineering and Applications, 2017, 53(7):115-120.
[24] LECUN Y, BOTTOU L, BENGIO Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11):2278-2324.
[25] 谢剑斌,兴军亮,张立宁,等.视觉机器学习20讲[M].北京:清华大学出版社,2015.

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed

基于SVD和DCNN的彩色图像多功能零水印算法

Multipurpose zero watermarking algorithm for color image based on SVD and DCNN

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 4

多维度评价

本文评价

推荐阅读 0

[1]	陈大伟,闫昭*,刘昊岩. SVD系列算法在评分预测中的过拟合现象[J]. 山东大学学报(工学版), 2014, 44(3): 15-21.
[2]	孙靖杰1,赵建军2*,姚跃亭3,姚刚1. 基于可变遗忘因子的改进RPCA方法及其在自适应故障监测中的应用[J]. 山东大学学报(工学版), 2012, 42(4): 60-66.
[3]	刁鸣,魏挺. 一种改进的二维ESPRIT算法[J]. 山东大学学报(工学版), 2010, 40(2): 149-152.
[4]	田伟,乔谊正,马志强 . 基于DWT的二次特征提取脱机中文签名鉴定[J]. 山东大学学报(工学版), 2007, 37(3): 55-59 .