基于两通道深度卷积神经网络的图像隐藏方法  

Image Hiding Method Based on Two-Channel Deep Convolutional Neural Network

作　　者：段新涛[1] 王文鑫 李磊 邵志强 王鲜芳 秦川[3] DUAN Xintao;WANG Wenxin;LI Lei;SHAO Zhiqiang;WANG Xianfang;QIN Chuan(College of Computer and Information Engineering,Henan Normal University,Xinxiang 453007,China;College of Computer Science and Technology,Henan Institute of Technology,Xinxiang 453003,China;School of Optical-Electrical and Computer Engineering,University of Shanghai for Science and Technology,Shanghai 200093,China)

机构地区：[1]河南师范大学计算机与信息工程学院,新乡453007 [2]河南工学院计算机科学与技术学院,新乡453003 [3]上海理工大学光电与计算机工程学院,上海200093

出　　处：《电子与信息学报》2022年第5期1782-1791,共10页Journal of Electronics & Information Technology

基　　金：国家自然科学基金(U1904123,61672354,62072157);教育人工智能与个性化学习河南省重点实验室基金。

摘　　要：现有的基于深度卷积神经网络(DCNN)实现的图像信息隐藏方法存在图像视觉质量差和隐藏容量低的问题。针对此类问题,该文提出一种基于两通道深度卷积神经网络的图像隐藏方法。首先,与以往的隐藏框架不同,该文提出的隐藏方法中包含1个隐藏网络和2个结构相同的提取网络,实现了在1幅载体图像上同时对2幅全尺寸秘密图像进行有效的隐藏和提取;其次,为了提高图像的视觉质量,在隐藏网络和提取网络中加入了改进的金字塔池化模块和预处理模块。在多个数据集上的测试结果表明,所提方法较现有的图像信息隐藏方法在视觉质量上有显著提升,载体图像PSNR和SSIM分别提高了3.75 dB和3.61%,实现的相对容量为2,同时具有良好的泛化能力。The existing image information hiding methods based on Deep Convolutional Neural Networks(DCNN)have the problems of poor image visual quality and low hiding capacity.Addressing such issues,an image hiding method based on a two-channel deep convolutional neural network is proposed.First,different from the previous hiding framework,the hiding method proposed in this paper includes one hiding network and two revealing networks with the same structure,and two full-size secret images can be effectively hidden and revealed at the same time is realized.Then,to improve the visual quality of the image,an improved pyramid pooling module and a preprocessing module are added to the hiding and revealing network.The test results on multiple data sets show that the proposed method has a significant improvement in visual quality compared with existing image information hiding methods.The Peak Signal-to-Noise Ratio(PSNR)and Structural SIMilarity(SSIM)values are increased by 3.75 dB and 3.61%respectively,a relative capacity of 2 and good generalization ability are achieved.

关 键 词：图像信息隐藏 深度卷积神经网络 金字塔池化 预处理 

分 类 号：TN911.73[电子电信—通信与信息系统] TP309.2[电子电信—信息与通信工程]