Focus Manipulation Detection via Photometric Histogram Analysis

doi:10.1109/CVPR.2018.00180

	Focus Manipulation Detection via Photometric Histogram Analysis
	Chen, Can 1; McCloskey, Scott 2; Yu, Jingyi3,4
	2018
会议录名称	2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
页码	1674-1682
发表状态	已发表
DOI	10.1109/CVPR.2018.00180
摘要	With the rise of misinformation spread via social media channels, enabled by the increasing automation and realism of image manipulation tools, image forensics is an increasingly relevant problem. Classic image forensic methods leverage low-level cues such as metadata, sensor noise fingerprints, and others that are easily fooled when the image is re-encoded upon upload to facebook, etc. This necessitates the use of higher-level physical and semantic cues that, once hard to estimate reliably in the wild, have become more effective due to the increasing power of computer vision. In particular, we detect manipulations introduced by artificial blurring of the image, which creates inconsistent photometric relationships between image intensity and various cues. We achieve 98% accuracy on the most challenging cases in a new dataset of blur manipulations, where the blur is geometrically correct and consistent with the scene's physical arrangement. Such manipulations are now easily generated, for instance, by smartphone cameras having hardware to measure depth, e.g. 'Portrait Mode' of the i-Phone7Plus. We also demonstrate good performance on a challenge dataset evaluating a wider range of manipulations in imagery representing 'in the wild' conditions.
出版地	345 E 47TH ST, NEW YORK, NY 10017 USA
会议地点	Salt Lake City, UT, United states
收录类别	CPCI ; CPCI-S ; EI
语种	英语
资助项目	Defense Advanced Research Projects Agency[FA8750-16-C-0190]
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:000457843601083
出版者	IEEE
EI入藏号	20191106642665
EI主题词	Computer vision ; Object recognition ; Photometry ; Semantics ; Social networking (online)
EI分类号	Computer Software, Data Handling and Applications:723 ; Computer Applications:723.5 ; Optical Variables Measurements:941.4
WOS关键词	DEPTH ; BLUR
原始文献类型	Proceedings Paper
引用统计	正在获取...
文献类型	会议论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/30284
专题	信息科学与技术学院_PI研究组_虞晶怡组
通讯作者	Chen, Can
作者单位	1.Univ Delaware, Comp Informat & Sci, Newark, DE 19716 USA 2.Honeywell ACS Labs, Golden Valley, MN 55422 USA 3.Univ Delaware, Newark, DE 19716 USA 4.ShanghaiTech Univ, Shanghai 200031, Peoples R China
推荐引用方式 GB/T 7714	Chen, Can,McCloskey, Scott,Yu, Jingyi. Focus Manipulation Detection via Photometric Histogram Analysis[C]. 345 E 47TH ST, NEW YORK, NY 10017 USA:IEEE,2018:1674-1682.