Detecting false captioning using common-sense reasoning

Sangwon Lee, David A. Shamma, Bruce Gooch

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

Detecting manipulated images has become an important problem in many domains (including medical imaging, forensics, journalism and scientific publication) largely due to the recent success of image synthesis techniques and the accessibility of image editing software. Many previous signal-processing techniques are concerned about finding forgery through simple transformation (e.g. resizing, rotating, or scaling), yet little attention is given to examining the semantic content of an image, which is the main issue in recent image forgeries. Here, we present a complete workflow for finding the anomalies within images by combining the methods known in computer graphics and artificial intelligence. We first find perceptually meaningful regions using an image segmentation technique and classify these regions based on image statistics. We then use AI common-sense reasoning techniques to find ambiguities and anomalies within an image as well as perform reasoning across a corpus of images to identify a semantically based candidate list of potential fraudulent images. Our method introduces a novel framework for forensic reasoning, which allows detection of image tampering, even with nearly flawless mathematical techniques.

Original languageEnglish
Pages (from-to)65-70
Number of pages6
JournalDigital Investigation
Volume3
Issue numberSUPPL.
DOIs
Publication statusPublished - 2006 Jan 1

Fingerprint

Medical imaging
Computer graphics
Image segmentation
Artificial intelligence
Signal processing
Journalism
Semantics
Statistics
Computer Graphics
Workflow
Artificial Intelligence
Diagnostic Imaging
Publications
Software
artificial intelligence
computer graphics
workflow
journalism
scaling
candidacy

All Science Journal Classification (ASJC) codes

  • Pathology and Forensic Medicine
  • Information Systems
  • Computer Science Applications
  • Medical Laboratory Technology
  • Law

Cite this

Lee, Sangwon ; Shamma, David A. ; Gooch, Bruce. / Detecting false captioning using common-sense reasoning. In: Digital Investigation. 2006 ; Vol. 3, No. SUPPL. pp. 65-70.
@article{e2a951529f3d4ad386a8fb0063ce4ad9,
title = "Detecting false captioning using common-sense reasoning",
abstract = "Detecting manipulated images has become an important problem in many domains (including medical imaging, forensics, journalism and scientific publication) largely due to the recent success of image synthesis techniques and the accessibility of image editing software. Many previous signal-processing techniques are concerned about finding forgery through simple transformation (e.g. resizing, rotating, or scaling), yet little attention is given to examining the semantic content of an image, which is the main issue in recent image forgeries. Here, we present a complete workflow for finding the anomalies within images by combining the methods known in computer graphics and artificial intelligence. We first find perceptually meaningful regions using an image segmentation technique and classify these regions based on image statistics. We then use AI common-sense reasoning techniques to find ambiguities and anomalies within an image as well as perform reasoning across a corpus of images to identify a semantically based candidate list of potential fraudulent images. Our method introduces a novel framework for forensic reasoning, which allows detection of image tampering, even with nearly flawless mathematical techniques.",
author = "Sangwon Lee and Shamma, {David A.} and Bruce Gooch",
year = "2006",
month = "1",
day = "1",
doi = "10.1016/j.diin.2006.06.006",
language = "English",
volume = "3",
pages = "65--70",
journal = "Digital Investigation",
issn = "1742-2876",
publisher = "Elsevier Limited",
number = "SUPPL.",

}

Detecting false captioning using common-sense reasoning. / Lee, Sangwon; Shamma, David A.; Gooch, Bruce.

In: Digital Investigation, Vol. 3, No. SUPPL., 01.01.2006, p. 65-70.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Detecting false captioning using common-sense reasoning

AU - Lee, Sangwon

AU - Shamma, David A.

AU - Gooch, Bruce

PY - 2006/1/1

Y1 - 2006/1/1

N2 - Detecting manipulated images has become an important problem in many domains (including medical imaging, forensics, journalism and scientific publication) largely due to the recent success of image synthesis techniques and the accessibility of image editing software. Many previous signal-processing techniques are concerned about finding forgery through simple transformation (e.g. resizing, rotating, or scaling), yet little attention is given to examining the semantic content of an image, which is the main issue in recent image forgeries. Here, we present a complete workflow for finding the anomalies within images by combining the methods known in computer graphics and artificial intelligence. We first find perceptually meaningful regions using an image segmentation technique and classify these regions based on image statistics. We then use AI common-sense reasoning techniques to find ambiguities and anomalies within an image as well as perform reasoning across a corpus of images to identify a semantically based candidate list of potential fraudulent images. Our method introduces a novel framework for forensic reasoning, which allows detection of image tampering, even with nearly flawless mathematical techniques.

AB - Detecting manipulated images has become an important problem in many domains (including medical imaging, forensics, journalism and scientific publication) largely due to the recent success of image synthesis techniques and the accessibility of image editing software. Many previous signal-processing techniques are concerned about finding forgery through simple transformation (e.g. resizing, rotating, or scaling), yet little attention is given to examining the semantic content of an image, which is the main issue in recent image forgeries. Here, we present a complete workflow for finding the anomalies within images by combining the methods known in computer graphics and artificial intelligence. We first find perceptually meaningful regions using an image segmentation technique and classify these regions based on image statistics. We then use AI common-sense reasoning techniques to find ambiguities and anomalies within an image as well as perform reasoning across a corpus of images to identify a semantically based candidate list of potential fraudulent images. Our method introduces a novel framework for forensic reasoning, which allows detection of image tampering, even with nearly flawless mathematical techniques.

UR - http://www.scopus.com/inward/record.url?scp=33746216093&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33746216093&partnerID=8YFLogxK

U2 - 10.1016/j.diin.2006.06.006

DO - 10.1016/j.diin.2006.06.006

M3 - Article

VL - 3

SP - 65

EP - 70

JO - Digital Investigation

JF - Digital Investigation

SN - 1742-2876

IS - SUPPL.

ER -