基于双通道R-FCN的图像篡改检测模型  

Dual-Channel R-FCN Model for Image Forgery Detection

作　　者：田秀霞 李华强 张琴 周傲英[3,4] TIAN Xiu-Xia;LI Hua-Qiang;ZHANG Qin;ZHOU Ao-Ying(College of Computer Science and Technology,Shanghai University of Electric Power,Shanghai 200090;Stale Grid Lanzhou Power Supply Company,Ministry of Internet,Information and Communication Security Laboratory,Lanzhou 730050;College of Data Science and Engineering,East China Normal University,Shanghai 200062;Shanghai Key Laboratory of Trustworthy Computing,Software Engineering Institute,East China Normal University,Shanghai 200062)

机构地区：[1]上海电力大学计算机科学与技术学院,上海200090 [2]国网兰州供电公司互联网部信息通信安全实验室,兰州730050 [3]华东师范大学数据科学与工程研究院,上海200062 [4]华东师范大学软件学院上海市高可信计算重点实验室,上海200062

出　　处：《计算机学报》2021年第2期370-383,共14页Chinese Journal of Computers

基　　金：国家自然科学基金(面上项目,重点项目)(61772327,61532021);国网甘肃省电力公司电力科学研究院横向项目(H2019-275)资助.

摘　　要：随着大数据时代的到来和图像编辑软件的发展,恶意篡改图片的数量出现井喷式增长,为了确保图像的真实性,众多学者基于深度学习和图像处理技术提出了多种图像篡改检测算法.然而,当前提出的绝大多数方法在面对大量图片的情况下,篡改检测速率较低且小面积篡改区域检测效果较差.为了有效解决这些问题,本文首次将基于区域的全卷积网络(Region-based Fully Convolutional Networks,R-FCN)引入双通道篡改检测网络,通过彩色图像通道提取图像的表层特征,使用隐写分析通道挖掘图像内部的统计特征,并利用双线性池化层将两个通道的信息融合,构建了一种面向实际应用场景的图像篡改检测模型.其中,利用R-FCN中位置敏感得分图提高图像篡改检测效率,使用双线性插值算法提高小面积篡改区域的检测率.通过在国际主流的标准图像篡改数据集上进行实验,有效地验证了该模型的图像篡改检测速率相比当前最新模型提高2.25倍,检测精度提升1.13%到3.21%,本文提出的模型是一种更加高效而精准的图像篡改检测模型.With the explosive growth of malicious tampering images,many scholars have proposed multiple image forgery detection algorithms based on deep learning and image processing technologies.Although these algorithms have achieved good results,most of them have strong limitations in practical application.In order to solve this problem,we proposed a dual-channel forgery detection model empowered by Region-based Full Convolution Network(R-FCN),which was inspired by the two-stream network.The model included two parts:RGB channel and steganalysis channel.The design of dual channel enables the model to capture more features in the image and obtain a better detection effect.First of all,the model utilized the properties of each channel to extract the image’s features.The RGB channel captured the boundary,color,texture and other surface features of the image,and analyzed the tampering artifacts which were left by image forgery.Steganalysis channel used the Spatial Rich Model(SRM) filter layer to extract the residual noise of the image,and analyzed the inconsistency between the real area and the tampering area.Then,the model used the Region Proposal Network(RPN) to obtain the corresponding Region of Interest(ROI)location information from the feature maps,and combined the position-sensitive ROI pooling operations to get the score maps.Finally,the model used the bilinear pooling layer to fuse the information of the two channels,and processed the relevant features to obtain the corresponding category information and location information,so as to located the tampering area.On the one hand,the proposed model uses the design of the position-sensitive score map in R-FCN,which increases the number of shared computing network layers by changing the location of the ROI pooling layer,and improves the detection efficiency.On the other hand,bilinear interpolation is used to adjusting the output size of the feature map in the feature extraction network,which alleviates the weak expression ability of model features caused by convolution op

关 键 词：图像篡改检测 深度学习 双通道网络 基于区域的全卷积网络 双线性插值 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置] TP183[自动化与计算机技术—控制理论与控制工程]