用户名: 密码: 验证码:
基于机器学习的音频盲水印方法研究
详细信息    本馆镜像全文|  推荐本文 |  |   获取CNKI官网全文
摘要
随着计算机网络和多媒体技术的飞速发展,多媒体数据逐渐成为人们获取信息的重要来源,并成为人们生活的重要组成部分。因而,作为数字媒体产品知识产权宣告及保护的有效工具,数字水印技术自1993年第一次提出以来已经引起了人们极大的关注,同时,如何保护多媒体信息的安全成为国际上研究的热门课题。特别是音频信号的数字水印技术已经成为近年来研究的热点之一。信息安全技术中采取的密码学技术因仅能控制信息的传播过程,而对于解码后的媒体数据却难以控制,因而无法阻止盗版者的非法拷贝和传播。作为解决上述问题的一种有效途径,数字水印技术开始引起人们的普遍关注。它通过在原始数据中嵌入秘密信息来证实数据的所有权或完整性,以此来抑制对数字作品的盗版或篡改。
     数字音频水印技术就是向载体数据(如音频信号)中嵌入秘密信息以达到版权宣告及保护的目的。数字水印技术的关键就是工作域和嵌入策略的选取,从某种程度上说,工作域和嵌入策略选取的好坏从根本上决定了整个数字水印系统的优劣。而近年发展起来的小波变换是一种新型的时频分析方法,具有很多良好的性质,特别适合于音频信号的处理。本文正是将小波变换应用到音频信号的数字水印系统中,提出一种小波域上基于机器学习方法的新的数字音频盲水印算法,使其能在水印的鲁棒性和不可感知性之间寻找到合理的平衡点,从而具有更良好透明性和鲁棒性,并在音频作品的版权保护中能有一定的实用性。
     本文的主要贡献如下:
     (1)提出一种基于支持向量回归机(Support Vector Regression,SVR)的鲁棒数字音频水印算法。算法的基本思想是先对整段音频信号进行分抽样处理,然后对所有的子音频分别进行小波变换,水印信号则嵌入到其中一个子音频信号的胁ū浠缓蟮牡推迪凳?水印提取时不需要原始音频信号。由于不同子音频信号之间的高度相关性,相应的DWT分解后的各小波低频系数分布也具有相似性。利用这种高度相关性,在嵌入和提取的过程应用SVR具有的非线性逼近能力,建立待嵌入的子音频信号与其他子音频信号之间的对应模板关系,再利用训练好的SVR提取水印,实现盲检测。
     (2)针对数字音频水印的鲁棒性和不可感知性两者之间是相互制约问题,提出一种采用遗传算法(Genetic Algorithms,GA)来解决最优嵌入能量的优化水印方案。遗传算法是通过群体进化来随机搜索目标函数的最优化问题,对于前述基于支持向量回归机的小波域数字音频盲水印算法,进一步地探讨采用遗传算在嵌入强度集合中搜索对抗攻击能力适应度较高的个体,从而得到最佳嵌入强度的一个优化方案,以实现自适应策略,也使本算法能在水印的鲁棒性和不可感知性之间寻找到合理的平衡点,从而具有更良好透明性和鲁棒性。
     仿真实验结果表明,两种方法都具有较强的鲁棒性和不可感知性,水印嵌入容量的自适应性,提取水印时不需要原始音频信号的参与,且对包括MP3有损压缩、低通滤波、重采样/重量化等多种攻击性试验具有较强的稳健性,是可行的数字音频水印算法。可以根据具体需求,用于数字音频作品的版权保护。
The digital media has become a main way for information communication along with the rapid development of digital technology and computer networks. As a useful tool for the copyright protection and judgment, digital watermarking technique has gained more and more concerns in many ways since it appeared in 1993, meanwhile, protection of digital multimedia information has become an increasingly important issue. Especially audio digital watermarking technique has been one of the research hotspots in recent years. Traditional information security system can only safeguard information transmitting process, but which can't control the decoded media data. So it can't prevent the illegal copy of the pirate. As a novel way to solve these problems, digital watermarking technology begins to be popularly researched and used. By embedding some secret watermark information in the host multimedia signals, it provides solutions to copyright protection and content verification.
     With the digital audio watermarking technique we can embed secret information into digital audio signal, so as to arrive at the purpose of copyright protection and judgment. The chose of the work field and the embed method becomes more necessary. Wavelet transform, as a new powerful tool of time-frequency analysis, provides several good characters that make it appropriate to audio signal watermarking. So, a novel machine learning based digital blind audio watermarking scheme in the wavelet domain is proposed in this paper, which could find a reasonable balance between the robustness and inaudibility of the watermark, then have the better robustness and inaudibility. And the proposed watermarking method which doesn't require the use of the original audio signal for watermark extraction also can provide a good copyright protection scheme.
     The main contribution of this paper is as follows:
     (1) This paper focuses mainly on a novel support vector regression (SVR) based digital audio watermarking scheme in the wavelet domain which using subsampling. The audio signal is subsampled firstly and all the sub-audios are decomposed into the wavelet domain respectively. Then the watermark information is embedded into the low-frequency region of random one sub-audio. With the high correlation among the sub-audios, accordingly, the distributing rule of different sub-audios in the wavelet domain is similar to each other, SVR can be used to learn the characteristics of them. Using the information of unmodified template positions in the low-frequency region of the wavelet domain, the SVR can be trained well. Thanks to the good learning ability of SVR, the watermark can be correctly extracted under several different attacks, and the proposed watermarking method which doesn't require the use of the original audio signal.
     (2) Aiming at the problem which is the robustness and inaudibility of the digital audio watermark is limited for each other, so an optimization watermarking method based on Genetic Algorithm (Genetic Algorithms, GA) which to compute the best energy quickly is proposed in this paper. Because the genetic algorithms could search the optimization of objective function randomly, which via the evolution of groups, our work is based on the embedding/detecting way of "DWT-Based Audio Watermarking Using Support Vector Regression and Subsampling". And this method provides a preliminary discussion on the application of GA, which searching the individual with the highest fitness of attack-resistance in the aggregate of the optimal embedding strength. As an optimization solution of obtaining the optimal embedding strength, it could achieve an adaptive policy, and find a reasonable balance between the robustness and inaudibility of the watermark, just for the better robustness and inaudibility in the algorithm.
     The experimental results show the two practical algorithms can preserve inaudibility and they are robust enough to against the different signal processing operations. In addition, the watermarking information can be embedded into the original audio signal adaptively, which also doesn't require the use of the original audio signal for detection. Furthermore, it can resist the different attacks, such as lossy compression (MP3), filtering, resampling and requantizing, etc. So it can be used for copyright protection of digital audio productions.
引文
[1]R.G.van Schyndel,A.Z.Tirkel,C.EOsbome:A digital watermark.First IEEE International Image Processing Conference,1994,2:86-90.
    [2]W.Bender,D.Gruhl,A.Lu:Echo hiding,in Proc.Information Hiding Workshop,University of Cambridge,U.K.,pp.295-315,(1996).
    [3]L.Boney,A.Tewfik,K.Hamdy:Digital watermarks for audio signals.IEEE Int.Conf.on Multimedia Computing and Systems,1996,1:473-480.
    [4]V.Vapnik:The Nature of Statistical Learning Theory.Springer-Verlag,New York(2001).
    [5]Vladimir V.Vapnik著,张学工译,“统计学习理论的本质,”清华大学出版社,2000.
    [6]J.F Delaigie:Human Visual System Features Enabling Watermarking[J].C 2002 IEEE,489-492.
    [7]张军.用于图像认证的基于神经网络的水印技术[J].计算机辅助设计与图形学学报,2003,15(3):307-312.
    [8]Jun Zhang:Hiding a Logo Watermark into the Multiwavelet Domain Using Neural Networks[c].Proceedings of the 14th 1EEE International Conference on Tools with Artificial Intelligence(ICTAI'02),2002.77.482.
    [9]刘振华、尹萍.信息隐藏技术及其应用,北京,科学出版社,2002。
    [10]S.Craver,N.Memon,B.-L.Yeo and M.M.Yeung:Resolving rightful ownerships with invisible watermarking techniques,IEEE Journal on Selected Areas in Communications,Volume:16 Issue:4,May 1998.Page(s)573-586.
    [11]Zeng W,Liu B:A statistical watermark detection technique without using original image for resolving rightful ownerships of digital images[J].IEEE Trans on Image Processing,1999,11(8):I 534-1548.
    [12]T.Painter,A.Spanias:Perceptual coding of digital audio.Proceedings of the IEEE,2000,88(4):451-513.
    [13]J.D.Johnston:Transform coding of audio signals using perceptual noise criteria.IEEE.Journal on Selected Areas in Communications,1998,6(2):314-323.
    [14]E.Ambikairajah,A.G.Davis,W.T.K.Wong:Auditory masking and MPEG-1 audio compression.IEEE Electronics and Communication Engineering Journal,1997,8:165-175.
    [15]杨行峻,迟惠生等.语音信号数字处理.北京:电子工业出版社,1995:34-46.
    [16]鲁瑞华.听觉特性在数字音频压缩编码中的应用.电声技术,1998,(5):6-12.
    [17]F.A.P.Pefitcolas,R.J.Anderson and M.G.Kuhn:Information hidings a survey,Proc.Of IEEE,1999,87(7):1062-1078.
    [18]W.Bender,D.Gruhl,N.Morimoto,and A.Lu:Techniques for data hiding.[J]IBM Systems Journal,1996,35(3&4):313-336.
    [19]P.Bassia,L.Pitas,N.Nikolaidis:Robust audio watermarking in the domain[J].IEEE Trans.Multimedia,2001,3(2):232-241.
    [20]J.F.Tilki,A.Beex:Encoding a hidden digital signature onto an audio signal using psychoacoustic masking.IEEE Southeastcon'97,1997,1:331-333.
    [21]J.F.Tilki and A.Beex:Encoding a hidden auxiliary channel onto a digital audio signal using psychoacoustic masking,IEEE Southeastcon'97,1997,1:331-333.
    [22]Ye Wang:A new watermarking method of digital audio content for copyright protection.Proof Icsp'98,1998,1:1420-1423
    [23]Won-Gyum Kim,Jong Chan Lee,and Won Don Lee:An audio watermarking scheme with hidden signatures,Proceedings of 2000 on Information Security,16-(th)World Computer Congress,2000.
    [24]钮心忻,杨义先.基于小波变换的数字水印隐藏与检测算法,计算机学报.2000,23(1):21-27.
    [25]张敏瑞,易克初.倒谱域音频与图像水印算法,西安电子科技大学学报.2003,12:30-33。
    [26]Huijuan Yang,Jagdish C.Patra-* and Chong W.Chan:An Artificial Neural Network-Based Scheme For Robust Watermarking of Audio Signals.IEEE(2002).
    [27]Jian Wang,Fuzong Lin:Digital Audio Watermarking Based on Artificial Neura Networks.MINI-MICRO SYSTEMS(2005).
    [28]Jian Wang,Fuzong Lin:Digital Audio Watermarking Based on Support Vector Machine.Journal of Computer Research and Development(2005).
    [29]Serap Kirbiz,Bilge Gunsel:Robust Audio Watermark Decoding by supervised learning.IEEE(2006).
    [30]王炳锡,陈琦,邓峰森.数字水印技术,西安电子科技大学出版社.2003。
    [31]F.Hartung,and B.Girod:Spread Spectrum Watermarking:Malicious Attacks and Counterattacks,in Proceedings of the SPIE 3657,Security and watermarking of Multimedia Contents,1999,pp.147-158.
    [32]M.Kutter,and F.A.P.Petitcolas:Fair Benchmarking for Image Watermarking Systems,in Proceedings of the SPIE 3657,Security and watermarking of Multimedia Contents,1999,pp.226-239.
    [33]Siwei Lyu and Hany Farid."Detecting Hidden Messages Using Higher Order Statistics and Support Vector Machines." The 5th International Workshop on Information Hiding,Noordwijkerhout,Netherlands,2002.
    [34]S.Gunn.:Support vector machines for classification and regression.Technical report,Intelligent Speech and Intelligent Systems(ISIS)Group,University of Southampton,1998,1-8.
    [35]Enrico Capobianco.:On support vectormachines and sparse approximation for random processes[J].Neurocomputing,2004,56:39 - 60.
    [36]Olivier Chapelle.Vladimr Vapnik.ChoosingMultiple Parameters for Support Vector Machines[J].Machine Learning,2002,46:131-159.
    [37]王剑,林福宗.基于支持向量机(SVM)的数字声音水印.计算机研究与发展.2005年.42(9),1605-1611(2005)。
    [38]陈国良,王煦法,庄镇泉,王东生.遗传算法及其应用EM3.北京:人民邮电出版社,1996。
    [39]C.I.Podilchuk,I.Pitas:Image-adaptive Watermarking Using Visual Model[J].IEEE J.Sel.Areas Commun.,1998,16(4):525-539.
    [40]Chin-Shiuh Shieh,H.C.Huang,F.H.Wang:Genetic Watermarking Based on Transform domain Techniques[J].Journat of Pattern Recognition,2004,37(3):555-565.
    [41]程培岩,梁进勇,程永强.基于贝尔模板的文本图像压缩及重构算法的研究[J],太原理工大学学报,2006(2):150-154。
    [42]Shih Y.Robust Watermarking and Compression for Medical Images Based on Genetic Algorithms[J].Information Sciences,2005,175(3).
    [43]张永平,苏广川.基于小波变换的音频水印算法,计算机工程与应用,2006年,42卷35期,24-26。
    [44]R.G.van Schyndel,A.Z.Tirkel,C.F.Osbome.A digital watermark.First IEEE International Image Processing Conference,1994,2:86-90.
    [45]郑晓势,赵彦玲等.基于量化的DCT域数字音频水印方法,计算机工程与应用,2006年42卷20期,41-43.
    [46]Y.Wang.:A new watermarking method of digital audio content for copyright protection.The 4th Int'l Conf.Signal Processing,Beijing,(1998).
    [47]陈琦,王炳锡.一种用于版权保护的音频数字水印算法.电声技术,2002,(1):48-50.
    [48]陶智,赵鹤鸣等.一种心理声学模型的自同步音频数字水印,微电子学与计算机,2006年,23卷4期,27-30。
    [49]M.D.Swanson,M.Kobayashi,A.H.Tewifik:Multimedia data-embedding and watermarking technologies.Proceddings of the IEEE,1998,86(6):1064-1087.
    [50]S.W.Foo,T.H.Yeo,D.Y.Huang.:An adaptive audio watermarking system.Proceedings of IEEE Region 10 International Conference on Electrical and Electronic Technology,2001,2:509-513.
    [51]胡昌华等.基于MATLAB的系统分析与设计-小波分析,西安电子科大出版社,2000。
    [52]徐达文,王让定,鲍吉龙.基于听觉感知模型的自适应音频数字水印算法,2006年42卷31期,68-70,126。
    [53]蒋一鸣,徐汀荣.一种基于DWT和DPT结合的音频水印算法,2007年6期,21-23。
    [54]施化吉,伍剑等.一种基于MDCT变换的组合压缩音频水印算法,2007年24期,202-204。
    [55]李淑云,李高峰.数字音频水印技术发展及应用,2007年27卷B06期,225-228。
    [56]李淑芝,汪爱莲.一种基于小波域的盲检测音频水印算法,2006年 11Z期,64-65,138。
    [57]Davis Pan,"A Tutorial on MPEG/Audio Compression",IEEE Multimedia Journal,volume 2,summer 1995,pp60-74.
    [58]谢玲,张家树等.一种基于非均匀离散傅立叶变换的鲁棒音频水印算法,2006年2卷9期,1711-1721。
    [59]温秀梅,李虹,司亚超.一种基于傅利叶域的音频水印嵌入算法,2006年07Z期,67-68。
    [60]http://www.mathworks.com/access/helpdesk/help/toolbox/wavelet/ch06_a13.shtml.

© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号

地址:北京市海淀区学院路29号 邮编:100083

电话:办公室:(+86 10)66554848;文献借阅、咨询服务、科技查新:66554700