基于FC-DenseNets-BC神经网络的光学水印重建方法  

Optical watermarking reconstruction method based on FC-DenseNets-BC neural network

作　　者：陈祺 申桐 李鹏飞[1,2] 孙刘杰[2,3] 郑继红[1,2] CHEN Qi;SHEN Tong;LI Pengfei;SUN Liujie;ZHENG Jihong(School of Optical-Electrical and Computer Engineering,University of Shanghai for Science and Technology,Shanghai 200093,China;Shanghai Key Laboratory of Modern Optical System,University of Shanghai for Science and Technology,Shanghai 200093,China;College of Publishing and Art Design,University of Shanghai for Science and Technology,Shanghai 200093,China)

机构地区：[1]上海理工大学光电信息与计算机工程学院,上海200093 [2]上海理工大学上海市现代光学系统重点实验室,上海200093 [3]上海理工大学出版印刷与艺术设计学院,上海200093

出　　处：《光学技术》2021年第2期223-230,共8页Optical Technique

基　　金：科技部重点研发计划,同轴全息光存储的基础理论与关键技术研究(2018YFA0701800);国家自然科学基金项目(61975122)。

摘　　要：提出了一种基于深度学习的光学水印重建方法,通过双随机相位加密的方法实现水印的加密,并将加密图像嵌入到宿主图像中,然后利用原水印图像与含水印宿主图像之间的物理关系,训练改进的神经网络FC-DenseNets-BC,得到可以重建原水印图像的网络模型。在传统光学水印技术中,含水印宿主图像质量和解密水印图像质量依赖于嵌入强度的选取(当嵌入强度较大时,含水印宿主图像质量低,解密水印图像质量高;当嵌入强度较小时,含水印宿主图像质量高,解密水印图像质量低),然而使用深度学习重建水印图像可以摆脱该依赖关系。研究结果表明,在嵌入强度低至0.05的情况下,所提方法仍能够重建出峰值信噪比在35dB以上的高质量水印图像,且具有一定的泛化性、安全性和抵抗噪声、剪切的能力。并进一步通过光学系统实验验证了方法的可行性和高效性。An optical watermarking reconstruction method based on deep learning is proposed.The watermark is encrypted by double random phase encryption and the encrypted image is embedded in the host image.Then the physical relationship between watermark image and watermarked host image is used to train an improved neural network.Using the model of FC-DenseNets-BC can reconstruct the watermark image.In the traditional optical watermarking technology,the quality of watermarked host image and decrypted watermark image depends on the selection of the embedding strength.However,using deep learning to reconstruct the watermark image can get rid of this dependency.The simulation results show that the method can reconstruct high-quality watermark image with peak signal-to-noise ratio over 35 dB even when the embedding strength is as low as 0.05.It also has a certain generalization,safety and ability to resist noise and shear.The feasibility and efficiency of this method are further verified by the experiment of optical system.

关 键 词：深度学习 光学水印 双随机相位加密 神经网络 

分 类 号：TN29[电子电信—物理电子学]