Detecting doctored images using camera response normality and consistency

Zhouchen Lint, Rongrong Wang, Xiaoou Tang, Heung Yeung Shum

Research output: Chapter in Book/Conference Proceeding/ReportConference Paper published in a bookpeer-review

107 Citations (Scopus)

Abstract

The advance in image/video editing techniques has facilitated people in synthesizing realistic imageshideos that may hard to be distinguished from real ones by visual examination. This poses a problem: how to differentiate real imageshideos from doctored ones? This is a serious problem because some legal issues may occur if there is no reliable way for doctored image/video detection when human inspection fails. Digital watermarking cannot solve this problem completely, We propose an approach that computes the response functions the camera by selecting appropriate patches in different ways. An image may be doctored if the response functions are abnormal or inconsistent to each other. The normality of the response functions is classified by a trained support vector machine (SVM). Experiments show that our method is effective for high-contrast images with many textureless edges.

Original languageEnglish
Title of host publicationProceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005
PublisherIEEE Computer Society
Pages1087-1092
Number of pages6
ISBN (Print)0769523722, 9780769523729
DOIs
Publication statusPublished - 2005
Externally publishedYes
Event2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005 - San Diego, CA, United States
Duration: 20 Jun 200525 Jun 2005

Publication series

NameProceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005
VolumeI

Conference

Conference2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005
Country/TerritoryUnited States
CitySan Diego, CA
Period20/06/0525/06/05

Fingerprint

Dive into the research topics of 'Detecting doctored images using camera response normality and consistency'. Together they form a unique fingerprint.

Cite this