中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 三维可视计算
A hybrid convolutional architecture for accurate image manipulation localization at the pixel-level

文献类型：期刊论文

作者Zhang, Yixuan1,3; Zhang, Jiguang2; Xu, Shibiao2
刊名MULTIMEDIA TOOLS AND APPLICATIONS
出版日期2021-01-22
页码16
关键词Manipulation localization Top-down detection Bottom-up segmentation DenseCRFs
ISSN号1380-7501
DOI10.1007/s11042-020-10211-1
通讯作者Xu, Shibiao(shibiao.xu@nlpr.ia.ac.cn)
英文摘要Advanced image processing techniques can easily edit images without leaving any visible traces, making manipulation detection and localization for forensics analysis a challenging task. Few studies can simultaneously locate tampered objects accurately and refine contours of tampered regions effectively. In this study, we propose an effective and novel hybrid architecture, named Pixel-level Image Tampering Localization Architecture (PITLArc), which integrates the advantages of top-down detection-based methods and bottom-up segmentation-based methods. Moreover, we provide a typical fusion implementation of our proposed hybrid architecture on one outstanding detection-based method (two-stream faster region-based convolutional neural network (RGB-N)) and two segmentation-based methods (Multi-Scale Convolution Neural Networks (MSCNNs) and Dual-domain Convolutional Neural Networks (DCNNs)) to evaluate the effectiveness of the proposed architecture. The three methods can be integrated into our proposed PITLArc to significantly improve their performance. Other detection and segmentation algorithms (not limited to the three aforementioned methods) can also be integrated into our architecture to improve their performance. Moreover, a Dense Conditional Random Fields (DenseCRFs)-based post-processing method is introduced to further optimize the details of tampered regions. Experiments validate the effectiveness of the proposed architecture.
资助项目NSFC[U1636102] ; NSFC[U1736214] ; NSFC[61802393] ; NSFC[61872356] ; National Key Technology RD Program[2016QY15Z2500] ; Project of Beijing Municipal Science & Technology Commission[Z181100002718001]
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:000610019400012
出版者SPRINGER
资助机构NSFC ; National Key Technology RD Program ; Project of Beijing Municipal Science & Technology Commission
源URL[http://ir.ia.ac.cn/handle/173211/42897]  
专题模式识别国家重点实验室_三维可视计算
通讯作者Xu, Shibiao
作者单位1.Chinese Acad Sci, Inst Informat Engn, State Key Lab Informat Secur, Beijing, Peoples R China
2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing, Peoples R China
3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing, Peoples R China
推荐引用方式
GB/T 7714		 Zhang, Yixuan,Zhang, Jiguang,Xu, Shibiao. A hybrid convolutional architecture for accurate image manipulation localization at the pixel-level[J]. MULTIMEDIA TOOLS AND APPLICATIONS,2021:16.
APA Zhang, Yixuan,Zhang, Jiguang,&Xu, Shibiao.(2021).A hybrid convolutional architecture for accurate image manipulation localization at the pixel-level.MULTIMEDIA TOOLS AND APPLICATIONS,16.
MLA Zhang, Yixuan,et al."A hybrid convolutional architecture for accurate image manipulation localization at the pixel-level".MULTIMEDIA TOOLS AND APPLICATIONS (2021):16.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。