融合多尺度特征与多分支预测的多操作检测网络  

Multi-manipulation Detection Network Combining Multi-scale Feature and Multi-branch Prediction

作　　者：朱新山 卢俊彦 甘永东 任洪昊 王洪泉 薛俊韬 陈颖 ZHU Xinshan;LU Junyan;GAN Yongdong;REN Honghao;WANG Hongquan;XUE Juntao;CHEN Ying(School of Electrical and Information Engineer,Tianjin University,Tianjin 300072,China;Beijing SGITG-ACCENTURE Information Technology Co.Ltd.,Beijing 100052,China)

机构地区：[1]天津大学电气自动化与信息工程学院,天津300072 [2]北京国网信通埃森哲信息技术有限公司,北京100052

出　　处：《湖南大学学报（自然科学版）》2023年第8期94-105,共12页Journal of Hunan University:Natural Sciences

基　　金：国家自然科学基金资助项目(61972282,61971303)。

摘　　要：面对不断进步的图像编辑技术,发展相应的图像取证技术显得尤为重要.针对现有图像篡改检测技术中存在的可检测操作类型单一、鲁棒性不强、篡改区域定位不足等问题,提出一种基于卷积神经网络的多操作图像篡改检测方案.在该网络中,通过构造基于残差块的卷积流以提取操作特征.然后,设计一个多尺度特征融合模块,实现不同尺寸的操作特征融合.最后,将融合后的操作特征输入多分支预测模块进行篡改类型预测与定位,得到多操作检测结果 .本文制作了多操作图像篡改数据集,对提出的网络模型进行训练和测试.实验结果表明,本文方案与主流的目标检测网络相比,能够更准确地对篡改区域进行定位,参数量更少,且对常见的图像后处理具有更好的鲁棒性.With the continuous development of image editing technologies,it is particularly significant to develop image forensics technologies for image content security.Most existing forensics methods concentrated on single image manipulation detection but with weak robustness and no considerations on tampering location.This paper presents a multi-manipulation image forgery detection method based on convolutional neural network.In this network,a convolution flow based on residual block is constructed to extract manipulation features.Then,a multi-scale feature fusion module is designed to achieve operational feature fusion at different scales.Finally,the fused manipulation features are fed into the multi-branch prediction module,predicting the type and location of each utilized manipulation as the multi-manipulation detection results.An image dataset produced by multiple typical image manipulations is built to train and test the proposed network.The experimental results show that the proposed scheme can recognize the type of tampered manipulations and locate the tampered area more accurately with fewer parameters,and has better robustness to common image post-processing operations, compared with the state-of-the-art object detection networks.

关 键 词：图像取证 多操作检测 目标检测 深度学习 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]