首页 > 论文 > 液晶与显示 > 35卷 > 2期(pp:180-188)

基于极限学习机和离散小波变换的视频水印算法

Video watermarking algorithm based on extreme learning machine and discrete wavelet transform

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

本文设计了一种基于极限学习机算法的离散小波变换域视频水印添加方法, 该方法包括水印嵌入和水印提取两个部分。在水印嵌入环节, 首先使用场景切换检测算法实现非重叠帧提取, 然后对非重叠帧的亮度分量进行5级离散小波变换提取第5级低频子边带系数矩阵, 通过系数矩阵构建训练数据集并通过极限学习机进行回归训练, 回归模型的输出矢量与水印子块对系数矩阵进行修正, 最后通过逆小波变换得到嵌入水印的视频帧序列。在水印提取环节, 对嵌入水印的视频帧序列与原始视频帧序列的亮度分量分别进行5级离散小波变换, 通过提取两个低频子边带系数矩阵的差异部分来得到水印子块, 将所有的子块重组便可得到完整水印。一系列实验显示, 本方法在多个指标下表现良好, 对多种攻击均具有鲁棒性。

Abstract

A discrete wavelet transform domain video watermarking approach based on extreme learning machine algorithm is designed. The approach includes watermark embedding and watermark extraction. In the watermark embedding process, the scene switching detection algorithm is used to realize non-overlapping frame extraction, and then the fifth-order discrete wavelet transform is applied to the luminance component of the non-overlapping frame to extract the fifth-order low-frequency sub-band coefficient matrix. The training data set is constructed by the coefficient matrix and the regression training is performed by the extreme learning machine. The output vector of the regression model and the watermark sub-block are used to correct the coefficient matrix. Finally, the sequence of video frames embedded in watermark is obtained by inverse discrete wavelet transform. In the watermark extraction process, a 5-level discrete wavelet transform is performed on the luminance component of the watermarked video frame sequence and the luminance component of the original video frame sequence, respectively. The watermark sub-block is obtained by extracting the difference portion of the two low-frequency sub-band coefficient matrices. A complete watermark can be obtained by reorganizing all the sub-blocks. A series of experiments show that the proposed approach is robust and extremely efficient.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TP394.1;TH691.9

DOI:10.3788/yjyxs20203502.0180

所属栏目:图像处理

基金项目:2019年度义乌工商职业技术学院科研项目(No.2019JD502-02)

收稿日期:2019-07-10

修改稿日期:2019-09-20

网络出版日期:--

作者单位    点击查看

王运兰:义乌工商职业技术学院 机电信息学院, 浙江 义乌 322000

联系人作者:王运兰(wangyunlan0710@126.com)

备注:王运兰(1979-), 女, 湖南常德人, 硕士, 讲师, 2011年于杭州电子科技大学获得硕士学位, 主要从事多媒体技术, 互联网技术和机器学习应用等方面的研究。

【1】易开祥.数字图象加密与数字水印技术研究 [D]. 浙江大学, 2001.
YI K X. Research on digital image encryption and digital watermarking [D]. Zhejiang University, 2001. (in Chinese)

【2】DHAOU D, JABRA B S, ZAGROUBA E. A review on anaglyph 3D image and video watermarking [J]. 3D Research, 2019, 10(2): 279-285.

【3】刘连山, 李人厚, 高琦. 视频数字水印技术综述 [J]. 计算机辅助设计与图形学学报, 2005, 17(3):379-386.
LIU L S, LI R H, GAO Q. The digital water marking technology for video: A survey [J]. Journal of Computer-Aided Design and Computer Graphics, 2005, 17(03):379-386. (in Chinese)

【4】吴佳楠, 王世刚, 张迪,等. 融合量子密钥真随机性的二值图像水印 [J]. 光学 精密工程, 2017, 25(11): 2968-2974.
WU J N, WANG S G, ZHANG D, et al. Binary image watermark fusion based on quantum key true randomness [J]. Optics and Precision Engineering, 2017, 25(11): 2968-2974. (in Chinese)

【5】王玉海, 朱长青, 苏守宝,等. 结合感知哈希与数字水印的遥感影像认证方法[J]. 光学 精密工程, 2016, 24(10s): 640-648.
WANG Y H, ZHU C Q, SU S B, et al. An authentication method based on perceptual hashing and watermarking for remote sensing image [J]. Optics and Precision Engineering, 2016, 24(10s): 640-648. (in Chinese)

【6】HARTUNG F, GIROD B. Watermarking of uncompressed and compressed video [J]. Signal. Processing, 1998, 66(3): 283–301.

【7】李新宇, 陈阳.基于DWT_SVD的盲检测鲁棒视频水印算法[J].计算机技术与发展, 2018, 28(9):123-126.
LI X Y, CHEN Y. A robust video watermarking algorithm for blind detection based on DWT_SVD [J]. Computer Technology and Development, 2018, 28(9):123-126. (in Chinese)

【8】张云鹏.基于尺度不变特征变换的鲁棒图像和视频水印算法研究 [D].山东大学, 2018.
ZHANG Y P. Research on robust image and video watermarking algorithms based on scale invariant feature transform [D]. Shandong University, 2018. (in Chinese)

【9】曹海燕, 冯桂, 韩雪, 等.基于深度图的3D-HEVC鲁棒视频水印算法 [J].计算机应用, 2019, 39(3):869-873.
CAO H Y, FENG G, HAN X, et al. 3D-HEVC robust video watermarking algorithm based on depth map [J]. Journal of Computer Applications, 2019, 39(3):869-873. (in Chinese)

【10】杨静, 郑耿峰.基于运动矢量的脆弱视频水印算法研究 [J].电子设计工程, 2017, 25(12):153-156.
YANG J, ZHENG G F. A fragile video watermarking algorithm based on motion vectors [J]. Electronic Design Engineering, 2017, 25(12):153-156. (in Chinese)

【11】岳岩冰.基于混沌加密的H.264视频水印技术研究 [D]. 西安: 西安电子科技大学, 2016.
YUE Y B. H.264 watermarking research based on chaotic encryption [D]. Xi’an: Xidian University, 2016. (in Chinese)

【12】朱光,丰米宁.基于半脆弱水印的图博档视频资源内容认证策略研究 [J].现代图书情报技术,2016(12): 76-84.
ZHU G, FENG M N. Content authentication for video resources of libraries, museums and archives with semifragile watermarking [J]. Data Analysis and Knowledge Discovery, 2016(12): 76-84. (in Chinese)

【13】黄修训,周霁婷,张文俊,等.基于多特征的半脆弱视频水印算法研究 [J].电子测量技术,2015,38(4): 58-63.
HUANG X X, ZHOU J T, ZHANG W J, et al. Research on semi-fragile video watermarking based on
multi-feature [J].Electronic Measurement Technology, 2015, 38(4): 58-63. (in Chinese)

【14】王晶. 立体图像脆弱和半脆弱水印技术及其应用研究 [D]. 宁波: 宁波大学, 2014.
WANG J. Research on stereoscopic image fragile and semifragile watermarking methods and their applications [D]. Ningbo: Ningbo University, 2014. (in Chinese)

【15】陆思烨,李鸿燕,孙健昊,宋泽,曹宇.基于双阈值灰度直方图的场景切换检测算法及实现 [J].上海工程技术大学学报, 2018,32(1): 91-94.
LU S Y, LI H Y, SUN J H, et al. Scene change detection algorithm and implementation based on double threshold gray histogram [J]. Journal of Shanghai University of Engineering Science, 2018, 32(1): 91-94. (in Chinese)

【16】DRYUCHENKO M A, SIROTA A A. Digital video watermarking method based on heteroassociative image compression and its implementation by artificial neural networks [J]. Computer Optics, 2019, 1202(1): 1001-1007.

【17】ANKIT R, ANURAG M, RAJNI B. A Novel fuzzy frame selection based watermarking scheme for MPEG-4 videos using Bi-directional extreme learning machine [J]. Applied Soft Computing Journal, 2018, 121(7): 47-52.

【18】HUANG G B, ZHU Q Y, SIEW C K. Extreme learning machine: a new learning scheme of feed-forward neural networks [C]. IEEE International Joint Conference on Neural Networks, Budapest, Hungary, 2004: 985-990.

【19】MAURO B, FRANCO B, ALESSANDRO P. Improved wavelet-based watermarking through pixel-wise masking [J]. IEEE Transactions on Image Processing, 2001, 10(5): 783-791.

引用该论文

WANG Yun-lan. Video watermarking algorithm based on extreme learning machine and discrete wavelet transform[J]. Chinese Journal of Liquid Crystals and Displays, 2020, 35(2): 180-188

王运兰. 基于极限学习机和离散小波变换的视频水印算法[J]. 液晶与显示, 2020, 35(2): 180-188

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF