载体独立的深度光照水印算法

doi:10.11959/j.issn.2096-109x.2022056

网络与信息安全学报 ›› 2022, Vol. 8 ›› Issue (4): 110-118.doi: 10.11959/j.issn.2096-109x.2022056

载体独立的深度光照水印算法

陈浩¹^,², 王锋¹^,², 张卫明¹^,², 俞能海¹^,²

¹ 中国科学技术大学网络空间安全学院，安徽合肥 230001
² 中国科学技术大学中国科学院电磁空间信息重点实验室，安徽合肥 230001

修回日期:2022-05-19 出版日期:2022-08-15 发布日期:2022-08-01
作者简介:陈浩（1993− ），男，辽宁本溪人，中国科学技术大学硕士生，主要研究方向为信息隐藏
王锋（1996− ），男，安徽潜山人，中国科学技术大学硕士生，主要研究方向为数字水印和深度学习
张卫明（1976− ），男，河北定州人，博士，中国科学技术大学教授、博士生导师，主要研究方向为信息隐藏、密码学、媒体内容安全和人工智能安全
俞能海（1964− ），男，安徽无为人，博士，中国科学技术大学教授、博士生导师，主要研究方向为图像视频处理与分析、计算机视觉与模式识别、信息隐藏与媒体内容安全、信息检索与数据挖掘
基金资助:
国家自然科学基金(U20B2047)

Carrier-independent deep optical watermarking algorithm

Hao CHEN¹^,², Feng WANG¹^,², Weiming ZHANG¹^,², Nenghai YU¹^,²

¹ School of Cyber Science and Technology, University of Science and Technology of China, Hefei 230001, China
² CAS Key Laboratory of Electromagnetic Space Information, University of Science and Technology of China, Hefei 230001, China

Revised:2022-05-19 Online:2022-08-15 Published:2022-08-01
Supported by:
The National Natural Science Foundation of China(U20B2047)

摘要/Abstract

摘要：

随着多媒体技术的发展与完善，数字产品的版权保护需求逐步增大。数字水印是一种保护数字产品版权的有效手段，它一般是通过在数字载体（如文本、图像等）中添加重要标识信息（即数字水印），使载体带有标识信息，但又不影响载体的正常使用。常见的数字水印嵌入方案是通过采用特定算法对载体进行修改来嵌入水印信息的。而在实际的应用场景中，有很多待保护的图像或物件（如艺术画作等）是不允许修改的。基于此背景，提出了一种新的载体独立的深度光照水印算法，在嵌入端通过可见光调制的方法来表达水印信息，从而实现在不对原始载体进行修改的前提下进行水印信息嵌入，并达到版权保护的目的。通过对人眼视觉系统进行分析，提出了基于交替式投影的水印模板图案来嵌入水印信息，使嵌入过程既不需要对原始载体进行修改，也不会影响人眼的视觉感官。而在提取端，设计了基于残差连接的水印提取网络，对采集的水印图像经透视变换后送入该网络来进行水印信息提取。实验在多种条件下进行，并与3种基准算法进行了对比。实验结果表明，所提算法生成的水印图像具有较小的视觉失真，且对“投影-拍摄”过程具有很强的鲁棒性。在不同距离、角度、光照等条件下，水印提取网络具有很高的水印信息提取准确率，且相比其他通用网络具有一定的优越性。

关键词: 数字水印, 人眼视觉系统, 光照水印, 深度神经网络

Abstract:

With the development of multimedia techniques, the demand for copyright protection of digital products has also gradually risen.Digital watermarking is an effective means to protect the copyright of digital products.It is generally made by adding important identification information (i.e., digital watermark) to a digital carrier (e.g., text, image, etc.), so that the carrier carries the identification information but does not affect the normal use of the carrier.The common digital watermark embedding scheme is to embed the watermark information by modifying the carrier via specific algorithms.In the actual application scenarios, there are many images or objects to be protected (such as art paintings, etc.) that are not allowed to be modified.Based on this background, a new carrier-independent deep optical watermarking algorithm was proposed, which can realize watermark information embedding without modifying the original carrier and achieve the purpose of copyright protection.Specifically, a new watermark template expression scheme at the embedding end was proposed, which expressed the watermark information by visible light modulation.By analyzing the visual system of human eyes, a watermark template pattern based on alternating projection was proposed to embed the watermark information, which made the embedding process neither require modification of the original carrier nor affect the visual senses of human eyes.At the extraction end, a watermark extraction network based on residual connection was designed, and the captured watermarked images were fed into this network after perspective transformation to extract the watermark information.The experiments were conducted under various conditions and comparisons with three baseline algorithms were made.The experimental results show that the proposed algorithm generates watermarked images with less visual distortion and is robust to the ＆quot;projecting-shooting＆quot; process.The watermark extraction network has high accuracy in extracting watermark information at different distances, angles and illumination conditions, and has certain advantages over other general networks.

Key words: digital watermarking, human visual system, optical watermarking, deep neural network

中图分类号:

TP309.2

陈浩, 王锋, 张卫明, 俞能海. 载体独立的深度光照水印算法[J]. 网络与信息安全学报, 2022, 8(4): 110-118.

Hao CHEN, Feng WANG, Weiming ZHANG, Nenghai YU. Carrier-independent deep optical watermarking algorithm[J]. Chinese Journal of Network and Information Security, 2022, 8(4): 110-118.

图/表 10

图1

图2

图3

图4

表1

表2

表3

表4

表5

表6

参考文献 34

[1]	COX I J , KILIAN J , LEIGHTON F T ,et al. Secure spread spectrum watermarking for multimedia[J]. IEEE Transactions on Image Processing, 1997,6(12): 1673-1687.
[2]	SWANSON M D , KOBAYASHI M , TEWFIK A H . Multimedia data-embedding and watermarking technologies[J]. Proceedings of the IEEE, 1998,86(6): 1064-1087.
[3]	HARTUNG F , KUTTER M . Multimedia watermarking techniques[J]. Proceedings of the IEEE, 1999,87(7): 1079-1107.
[4]	LANGELAAR G C , SETYAWAN I , LAGENDIJK R L . Watermarking digital image and video data.A state-of-the-art overview[J]. IEEE Signal Processing Magazine, 2000,17(5): 20-46.
[5]	LIU Z . New trends and challenges in digital watermarking technology:applications for printed materials[M]// Multimedia Watermarking Techniques and Applications.Auerbach Publications. 2006: 257-305.
[6]	HAITSMA J , KALKER T . A watermarking scheme for digital cinema[C]// Proceedings of Proceedings 2001 International Conference on Image Processing (Cat.No.01CH37205). 2001: 487-489.
[7]	Digital Cinema Initiatives. Digital Cinema System specificationv1.2[R]. 2008.
[8]	常玉红, 黄惠芬, 王志红 . 检测图像篡改的脆弱水印技术[J]. 网络与信息安全学报, 2017,3(7): 47-52.
	CHANG Y H , HUANG H F , WANG Z H . Fragile watermarking technique for detecting image[J]. Chinese Journal of Network and Information Security, 2017,3(7): 47-52.
[9]	刘文星, 陈伟, 刘渊 . 图像四叉树剖分下的自适应数字水印算法[J]. 网络与信息安全学报, 2017,3(12): 40-47.
	LIU W X , CHEN W , LIU Y . Adaptive digital watermarking algo-rithm under image quad-tree partition[J]. Chinese Journal of Net-work and Information Security, 2017,3(12): 40-47.
[10]	王志红, 黄惠芬, 常玉红 . 基于SVD分解和Hadamard变换的图像半脆弱水印技术[J]. 网络与信息安全学报, 2017,3(5): 26-31.
	WANG Z H , HUANG H F , CHANG Y H . Semi-fragile watermark-ing technology based on SVD decomposition and Hadamard trans-form[J]. Chinese Journal of Network and Information Security, 2017,3(5): 26-31.
[11]	GOHSHI S , NAKAMURA H , ITO H ,et al. A new watermark surviving after re-shooting the images displayed on a screen[C]// Knowledge-Based Intelligent Information and Engineering Systems, 2005: 1099-1107.
[12]	OKIHARA K , INAZUMI Y , KINOSHITA H . A watermarking method that improves the relationship between of the number of embedded bits and image degradation[J]. The Journal of the Institute of Image Information and Television Engineers, 2004,58(10): 1465-1467.
[13]	UEHIRA K , SUZUKI K , IKEDA H . Does optoelectronic watermark technology migrate into business and industry in the near Future? Applications of optoelectronic watermarking technology to new business and industry systems utilizing flat-panel displays and smart devices[J]. IEEE Transactions on Industry Applications, 2016,52(1): 511-520.
[14]	UEHIRA K , SUZUKI K , IKEDA H . Applications of optoelectronic watermarking technique to new business and industry systems utilizing flat-panel displays and smart devices[C]// Proceedings of 2014 IEEE Industry Application Society Annual Meeting. 2014: 1-9.
[15]	UEHIRA K , SUZUKI M . Digital watermarking technique using brightness-modulated light[C]// Proceedings of 2008 IEEE International Conference on Multimedia and Expo. 2008: 257-260.
[16]	ISHIKAWA Y , UEHIRA K , YANAKA K . Practical evaluation of illumination watermarking technique using orthogonal transforms[J]. Journal of Display Technology, 2010,6(9): 351-358.
[17]	UEHIRA K , UNNO H . Effects of JPEG compression on reading optical watermarking embedded by using color-difference modulation[J]. Journal of Computer and Communications, 2018,6(1): 56-64.
[18]	OSHITA K , UNNO H , UEHIRA K . Optically written watermarking technology using temporally and spatially luminance-modulated light[J]. Electronic Imaging, 2016,28(8): 1-6.
[19]	UNNO H , UEHIRA K . Lighting technique for attaching invisible information onto real objects using temporally and spatially color-intensity modulated light[J]. IEEE Transactions on Industry Applications, 2020,56(6): 7202-7207.
[20]	UNNO H , YAMKUM R , BUNPORN C ,et al. A new displaying technology for information hiding using temporally brightness modulated pattern[J]. IEEE Transactions on Industry Applications, 2017,53(1): 596-601.
[21]	UNNO H , UEHIRA K . Display technique for embedding information in real object images using temporally and spatially luminance-modulated light[J]. IEEE Transactions on Industry Applications, 2017,53(6): 5966-5971.
[22]	BOSE R C , RAY-CHAUDHURI D K , . On a class of error correcting binary group codes[J]. Information and Control, 1960,3(1): 68-79.
[23]	PETERSON W W , BROWN D T . Cyclic codes for error detection[J]. Proceedings of the IRE, 1961,49(1): 228-235.
[24]	HE K M , ZHANG X Y , REN S Q ,et al. Deep residual learning for image recognition[C]// Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. 2016: 770-778.
[25]	LIN T Y , MAIRE M , BELONGIE S ,et al. Microsoft COCO:common objects in context[C]// Computer Vision – ECCV 2014. 2014: 740-755.
[26]	The USC-SIPI Image Database[EB].
[27]	SZEGEDY C , LIU W , JIA Y Q ,et al. Going deeper with convolutions[C]// Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition. 2015: 1-9.
[28]	YANG T J , CHEN Y H , SZE V . Designing energy-efficient convolutional neural networks using energy-aware pruning[C]// Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. 2017: 6071-6079.
[29]	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.
[30]	LIU C , ZOPH B , NEUMANN M . Progressive neural architecture search[J]. Computer Vision and Pattern Recognition, 2017.
[31]	SIMONYAN K , ZISSERMAN A . Very Deep convolutional networks for large-scale visual recognition[J]. Computer Vision and Pattern Recognition, 2014.
[32]	TAN M , LE Q . EfficientNet:rethinking model scaling for convolutional neural networks[C]// ICML. 2019.
[33]	HUANG G , LIU Z , VAN DER MAATEN L ,et al. Densely connected convolutional networks[C]// Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. 2017: 2261-2269.
[34]	GALLA T . Theory of neural information processing systems[J]. Journal of Physics A, 2006,39:3849.

算法	MOS
DCT^[10]	2.63
WHT^[11]	2.87
Color-D^[13]	3.26
本文算法	4.28

光照强度/(cd/m²)	误码率
光照强度/(cd/m²)	DCT^[15]算法	WHT^[16]算法	Color-D^[17]算法	本文算法
50	23.53%	24.07%	19.53%	7.23%
100	19.78%	24.33%	17.69%	5.49%
150	14.25%	11.05%	12.42%	4.88%
200	14.38%	12.26%	9.07%	3.24%

距离/cm	误码率
距离/cm	DCT^[15]算法	WHT^[16]算法	Color-D^[17]算法	本文算法
30	8.29%	9.38%	7.26%	1.26%
40	12.16%	10.26%	10.33%	1.33%
50	23.05%	20.02%	15.01%	3.41%
60	22.09%	19.03%	20.21%	5.71%
70	27.65%	22.70%	23.52%	9.24%

角度	误码率
角度	DCT^[15]算法	WHT^[16]算法	Color-D^[17]算法	本文算法
左40°	23.75%	19.28%	19.35%	13.24%
左30°	20.09%	19.05%	17.26%	6.43%
左15°	14.27%	16.93%	11.28%	5.27%
右15°	13.73%	24.65%	14.38%	7.26%
右30°	18.22%	20.96%	15.33%	11.48%
右40°	30.35%	22.49%	23.26%	15.33%
上40°	22.44%	19.72%	20.20%	17.96%
上30°	24.96%	21.04%	12.33%	7.24%
上15°	16.28%	20.62%	9.03%	3.23%
下15°	17.96%	12.53%	11.24%	7.96%
下30°	20.35 %	22.01%	18.73%	12.48%
下40°	30.05%	26.28%	28.62%	17.39%

JPEG压缩质量因子	误码率
JPEG压缩质量因子	DCT^[15]算法	WHT^[16]算法	Color-D^[17]算法	本文算法
10	19.62%	15.30%	17.64%	4.07%
20	11.45%	9.22%	10.23%	3.69%
30	9.73%	9.09%	7.64%	4.24%

载体独立的深度光照水印算法

Carrier-independent deep optical watermarking algorithm

在线阅读

pdf下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献 34

相关文章 6

Metrics

推荐阅读 0

网络	误码率
GoogLeNet^[27]	3.56%
MobileNet^[28]	4.58%
LeNet^[29]	6.37%
PNASNet^[30]	4.93%
VGGNet^[31]	4.65%
EfficientNet^[32]	4.73%
DenseNet^[33]	4.54%
DPN^[34]	4.77%
本文网络	1.97%

[1]	超凡,杨智,杜学绘,孙彦. 基于深度神经网络的Android恶意软件检测方法[J]. 网络与信息安全学报, 2020, 6(5): 67-79.
[2]	毕仁万,陈前昕,熊金波,刘西蒙. 面向深度神经网络的安全计算协议设计方法[J]. 网络与信息安全学报, 2020, 6(4): 130-139.
[3]	严飞,张铭伦,张立强. 基于边界值不变量的对抗样本检测方法[J]. 网络与信息安全学报, 2020, 6(1): 38-45.
[4]	谭亦夫,李子臣. 基于Shamir门限秘密分享的图像可视加密算法[J]. 网络与信息安全学报, 2018, 4(7): 69-76.
[5]	曹玉强,龚卫国,柏森. 基于多模生物模板安全的顽健图像隐藏算法[J]. 网络与信息安全学报, 2016, 2(9): 22-29.
[6]	蒋翠玲,黄帅,吴安雯,于文欣,康周茂,李永强. 基于PDF417二维条码的顽健数字水印方法[J]. 网络与信息安全学报, 2016, 2(9): 72-81.