Distinguishing Between Natural and Computer-Generated Images Using Convolutional Neural Networks
文献类型：期刊论文
| 作者 | Quan, Weize1,2,3 ; Wang, Kai3; Yan, Dong-Ming1,2; Zhang, Xiaopeng1,2
|
| 刊名 | IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
 |
| 出版日期 | 2018-11-01 |
| 卷号 | 13期号:11页码:2772-2787 |
| 关键词 | Image forensics natural image computer-generated image convolutional neural network robustness local-to-global strategy visualization |
| ISSN号 | 1556-6013 |
| DOI | 10.1109/TIFS.2018.2834147 |
| 通讯作者 | Yan, Dong-Ming(yandongming@gmail.com) |
| 英文摘要 | Distinguishing between natural images (NIs) and computer-generated (CG) images by naked human eyes is difficult. In this paper, we propose an effective method based on a convolutional neural network (CNN) for this fundamental image forensic problem. Having observed the rather limited performance of training existing CCNs from scratch or fine-tuning pretrained network, we design and implement a new and appropriate network with two cascaded convolutional layers at the bottom of a CNN. Our network can be easily adjusted to accommodate different sizes of input image patches while maintaining a fixed depth, a stable structure of CNN, and a good forensic performance. Considering the complexity of training CNNs and the specific requirement of image forensics, we introduce the so-called local-to-global strategy in our proposed network. Our CNN derives a forensic decision on local patches, and a global decision on a full-sized image can be easily obtained via simple majority voting. This strategy can also be used to improve the performance of existing methods that are based on hand-crafted features. Experimental results show that our method outperforms existing methods, especially in a challenging forensic scenario with NIs and CG images of heterogeneous origins. Our method also has good robustness against typical post-processing operations, such as resizing and JPEG compression. Unlike previous attempts to use CNNs for image forensics, we try to understand what our CNN has learned about the differences between NIs and CG images with the aid of adequate and advanced visualization tools. |
| WOS关键词 | DISCRIMINATION ; GRAPHICS ; FACES |
| 资助项目 | National Natural Science Foundation of China[61772523] ; National Natural Science Foundation of China[61620106003] ; National Natural Science Foundation of China[61331018] ; French National Agency for Research through PERSYVAL-lab[ANR-11-LABX-0025-01] ; DEFALS[ANR-16-DEFA-0003] |
| WOS研究方向 | Computer Science ; Engineering |
| 语种 | 英语 |
| WOS记录号 | WOS:000433909100005 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 资助机构 | National Natural Science Foundation of China ; French National Agency for Research through PERSYVAL-lab ; DEFALS |
| 源URL | [http://ir.ia.ac.cn/handle/173211/21683]  |
| 专题 | 自动化研究所_模式识别国家重点实验室_多媒体计算与图形学团队 |
| 通讯作者 | Yan, Dong-Ming |
| 作者单位 | 1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 3.Univ Grenoble Alpes, CNRS, Grenoble INP, GIPSA Lab, F-38000 Grenoble, France |
| 推荐引用方式 GB/T 7714 | Quan, Weize,Wang, Kai,Yan, Dong-Ming,et al. Distinguishing Between Natural and Computer-Generated Images Using Convolutional Neural Networks[J]. IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY,2018,13(11):2772-2787. |
| APA | Quan, Weize,Wang, Kai,Yan, Dong-Ming,&Zhang, Xiaopeng.(2018).Distinguishing Between Natural and Computer-Generated Images Using Convolutional Neural Networks.IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY,13(11),2772-2787. |
| MLA | Quan, Weize,et al."Distinguishing Between Natural and Computer-Generated Images Using Convolutional Neural Networks".IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 13.11(2018):2772-2787. |
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。