通信学报 ›› 2019, Vol. 40 ›› Issue (4): 171-178.doi: 10.11959/j.issn.1000-436x.2019086

• 学术论文 • 上一篇    下一篇

基于U型检测网络的图像篡改检测算法

王珠珠   

  1. 西安电子科技大学网络与信息安全学院,陕西 西安 710071
  • 修回日期:2019-03-01 出版日期:2019-04-25 发布日期:2019-05-05
  • 作者简介:王珠珠(1981- ),女,山东曹县人,西安电子科技大学博士生,主要研究方向为数据安全、人工智能安全。
  • 基金资助:
    陕西省自然科学基础研究计划基金资助项目(2016JM6074)

Image forgery detection algorithm based on U-shaped detection network

Zhuzhu WANG   

  1. School of Cyber Engineering,Xidian University,Xi’an 710071,China
  • Revised:2019-03-01 Online:2019-04-25 Published:2019-05-05
  • Supported by:
    The Natural Science Basic Research Plan in Shaanxi Province of China(2016JM6074)

摘要:

针对图像篡改检测算法依赖单一图像属性、适用度不高以及当前基于深度学习的检测算法时间复杂度过高、精度较低等缺陷,提出了一种基于U型检测网络的图像篡改检测算法。该算法首先利用连续的卷积层和最大池化层提取图像中多阶段的特征信息,然后将得到的特征信息通过上采样操作恢复至输入图像的分辨率大小。同时,为保证在提取图像高级语义信息的同时实现更高的检测精度,U型检测网络中各阶段的输出特征会和对应的通过上采样层的输出特征进行合并。U型检测网络在一般网络展现出来的特性上,进一步探究了图像中篡改与非篡改区域间的隐藏特征信息,利用其端到端的网络结构和提取图像上下文间较强关联信息的属性,可以实现快速且高精度的检测效果。最后利用全连接条件随机场对U型检测网络的输出结果进行优化,以获得更精细的检测效果。实验结果表明,所提算法效果优于传统的基于图像单一属性的篡改检测算法和当前基于深度学习的检测算法,并且具有较好的顽健性。

关键词: U型检测网络, 隐藏特征信息, 全连接条件随机场, 图像篡改检测

Abstract:

Aiming at the defects of traditional image tampering detection algorithm relying on single image attribute,low applicability and current high time-complexity detection algorithm based on deep learning,an U-shaped detection network image forgery detection algorithm was proposed.Firstly,the multi-stage feature information in the image by using the continuous convolution layers and the max-pooling layers was extracted by U-shaped detection network,and then the obtained feature information to the resolution of the input image through the upsampling operation was restored.At the same time,in order to ensure higher detection accuracy while extracting high-level semantic information of the image,the output features of each stage in U-shaped detection network would be merged with the corresponding output features through the upsampling layer.Further the hidden feature information between tampered and un-tampered regions in the image upon the characteristics of the general network was explored by U-shaped detection network,which could be realized quickly by using its end-to-end network structure and extracting the attributes of strong correlation information among image contexts that could ensure high-precision detection results.Finally,the conditional random field was used to optimize the output of the U-shaped detection network to obtain a more exact detection results.The experimental results show that the proposed algorithm outperforms those traditional forgery detection algorithms based on single image attribute and the current deep learning-based detection algorithm,and has good robustness.

Key words: U-shaped detection network, hidden feature information, conditional random field, image forgery detection

中图分类号: 

  • TP302