毕秀丽¹,
魏杨¹,
肖斌^1,,,
李伟生¹,
马建峰²
1.重庆邮电大学计算智能重点实验室 ??重庆 ??400065
2.西安电子科技大学网络与信息安全学院 西安 710071
基金项目:国家自然科学基金(61572092, U1401252)，国家重点研发计划基金(2016YFC1000307-3)

详细信息

作者简介:毕秀丽：女，1982年生，副教授，研究方向包括图像处理、多媒体安全和图像取证
魏杨：男，1993年生，硕士生，研究方向包括深度学习、图像取证
肖斌：男，1982年生，教授，研究方向包括图像处理、模式识别和数字水印
李伟生：男，1975年生，教授，研究方向包括智能信息处理与模式识别
马建峰：男，1963年生，教授，研究方向包括计算机网络、信息安全

通讯作者:肖斌　xiaobin@cqupt.edu.cn

¹⁾ CASIA v2.0：<http://forensics.idealtest.org/casiav2/>
中图分类号:TP309.2

计量

文章访问数:4087
HTML全文浏览量:1661
PDF下载量:146
被引次数:0

出版历程

收稿日期:2019-01-15
修回日期:2019-04-19
网络出版日期:2019-05-21
刊出日期:2019-12-01

Image Forgery Detection Algorithm Based on Cascaded Convolutional Neural Network

Xiuli BI¹,
Yang WEI¹,
Bin XIAO^1,,,
Weisheng LI¹,
Jianfeng MA²
1. Chongqing Key Laboratory of Computational Intelligence, Chongqing University of Posts and Telecommunications, Chongqing 400065, China
2. School of Computer Science and Technology, Xidian University, Xi’an 710071, China
Funds:The National Natural Science Foundation of China (61572092, U1401252), The National Science & Technology Major Project (2016YFC1000307-3)


摘要
摘要:基于卷积神经网络的图像篡改检测算法利用卷积神经网络的学习能力可以实现不依赖于单一图像属性的图像篡改检测，弥补传统图像篡改检测方法依赖单一图像属性、适用度不高的缺陷。利用深层多神经元的单一网络结构的图像篡改检测算法虽然可以学习更高级的语义信息，但检测定位篡改区域效果并不理想。该文提出一种基于级联卷积神经网络的图像篡改检测算法，在卷积神经网络所展示出来的普遍特性的基础上进一步探究其深层次的特性，利用浅层稀神经元的级联网络结构弥补以往深层多神经元的单一网络结构在图像篡改检测中的缺陷。该文提出的检测算法由级联卷积神经网络和自适应筛选后处理两部分组成，级联卷积神经网络实现分级式的篡改区域定位，自适应筛选后处理对级联卷积神经网络的检测结果进行优化。通过实验对比，该文算法展示了较好的检测效果，且具有较高的鲁棒性。
关键词:图像篡改检测/
级联卷积神经网络/
浅层稀神经元/
级联网络结构/
自适应筛选后处理
Abstract:The image forgery detection algorithm based on convolutional neural network can implement the image forgery detection that does not depend on a single image attribute by using the learning ability of convolutional neural network, and make up for the defect that the previous image forgery detection algorithm relies on a single image attribute and has low applicability. Although the image forgery detection algorithm using a single network structure of deep layers and multiple neurons can learn more advanced semantic information, the result of detecting and locating forgery regions is not ideal. In this paper, an image forgery detection algorithm based on cascaded convolutional neural network is proposed. Based on the general characteristics exhibited by convolutional neural network, and then the deeper characteristics are further explored. The cascaded network structure of shallow layers and thin neurons figures out the defect of the single network structure of deep layers and multiple neurons in image forgery detection. The proposed detection algorithm in this paper consists of two parts: the cascade convolutional neural network and the adaptive filtering post-processing. The cascaded convolutional neural network realizes hierarchical forgery regions localization, and then the adaptive filtering post-processing further optimizes the detection result of the cascaded convolutional neural network. Through experimental comparison, the proposed detection algorithm shows better detection results and has higher robustness.
Key words:Image forgery detection/
Cascaded convolutional neural network/
Shallow layers and thin neurons/
Cascaded network structure/
Adaptive filtering post-processing
注释:
1) ¹⁾ CASIA v2.0：<http://forensics.idealtest.org/casiav2/>



PDF全文下载地址:

https://jeit.ac.cn/article/exportPdf?id=1aacd760-2b77-4df2-a7be-ad585d8bd7f2