Signature-based image identification

Mohamed Abdel-Mottaleb, Gandhi Vaithilingam, Santhana Krishnamachari

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)

Abstract

The use of digital images and video is growing on the Internet and on consumer devices. Digital images and video are easy to manipulate, but this ease of manipulation makes tampering with digital content possible. Examples of the misuse of digital content include violating copyrights of the content and tampering with important material such as contents of video surveillance. In this paper we present an algorithm that extracts a binary signature from an image. This approach can be used to search for possible copyright violations by finding images with signatures close to that of a given image. The experimental results show that the algorithm can be very effective in helping users to retrieve sets of almost identical images from large collections of images. The signature can also be used for tamper detection. We will show that the signatures we extract are immune to quantization errors that result from compression and decompression.

Original languageEnglish (US)
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
PublisherSociety of Photo-Optical Instrumentation Engineers
Pages22-28
Number of pages7
Volume3845
StatePublished - 1999
Externally publishedYes
EventProceedings of the 1999 Multimedia Systems and Applications II - Boston, MA, USA
Duration: Sep 20 1999Sep 22 1999

Other

OtherProceedings of the 1999 Multimedia Systems and Applications II
CityBoston, MA, USA
Period9/20/999/22/99

Fingerprint

signatures
Internet
pressure reduction
surveillance
manipulators

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Condensed Matter Physics

Cite this

Abdel-Mottaleb, M., Vaithilingam, G., & Krishnamachari, S. (1999). Signature-based image identification. In Proceedings of SPIE - The International Society for Optical Engineering (Vol. 3845, pp. 22-28). Society of Photo-Optical Instrumentation Engineers.

Signature-based image identification. / Abdel-Mottaleb, Mohamed; Vaithilingam, Gandhi; Krishnamachari, Santhana.

Proceedings of SPIE - The International Society for Optical Engineering. Vol. 3845 Society of Photo-Optical Instrumentation Engineers, 1999. p. 22-28.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abdel-Mottaleb, M, Vaithilingam, G & Krishnamachari, S 1999, Signature-based image identification. in Proceedings of SPIE - The International Society for Optical Engineering. vol. 3845, Society of Photo-Optical Instrumentation Engineers, pp. 22-28, Proceedings of the 1999 Multimedia Systems and Applications II, Boston, MA, USA, 9/20/99.
Abdel-Mottaleb M, Vaithilingam G, Krishnamachari S. Signature-based image identification. In Proceedings of SPIE - The International Society for Optical Engineering. Vol. 3845. Society of Photo-Optical Instrumentation Engineers. 1999. p. 22-28
Abdel-Mottaleb, Mohamed ; Vaithilingam, Gandhi ; Krishnamachari, Santhana. / Signature-based image identification. Proceedings of SPIE - The International Society for Optical Engineering. Vol. 3845 Society of Photo-Optical Instrumentation Engineers, 1999. pp. 22-28
@inproceedings{fab7206481544d7083d62205bd53ed89,
title = "Signature-based image identification",
abstract = "The use of digital images and video is growing on the Internet and on consumer devices. Digital images and video are easy to manipulate, but this ease of manipulation makes tampering with digital content possible. Examples of the misuse of digital content include violating copyrights of the content and tampering with important material such as contents of video surveillance. In this paper we present an algorithm that extracts a binary signature from an image. This approach can be used to search for possible copyright violations by finding images with signatures close to that of a given image. The experimental results show that the algorithm can be very effective in helping users to retrieve sets of almost identical images from large collections of images. The signature can also be used for tamper detection. We will show that the signatures we extract are immune to quantization errors that result from compression and decompression.",
author = "Mohamed Abdel-Mottaleb and Gandhi Vaithilingam and Santhana Krishnamachari",
year = "1999",
language = "English (US)",
volume = "3845",
pages = "22--28",
booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",
publisher = "Society of Photo-Optical Instrumentation Engineers",

}

TY - GEN

T1 - Signature-based image identification

AU - Abdel-Mottaleb, Mohamed

AU - Vaithilingam, Gandhi

AU - Krishnamachari, Santhana

PY - 1999

Y1 - 1999

N2 - The use of digital images and video is growing on the Internet and on consumer devices. Digital images and video are easy to manipulate, but this ease of manipulation makes tampering with digital content possible. Examples of the misuse of digital content include violating copyrights of the content and tampering with important material such as contents of video surveillance. In this paper we present an algorithm that extracts a binary signature from an image. This approach can be used to search for possible copyright violations by finding images with signatures close to that of a given image. The experimental results show that the algorithm can be very effective in helping users to retrieve sets of almost identical images from large collections of images. The signature can also be used for tamper detection. We will show that the signatures we extract are immune to quantization errors that result from compression and decompression.

AB - The use of digital images and video is growing on the Internet and on consumer devices. Digital images and video are easy to manipulate, but this ease of manipulation makes tampering with digital content possible. Examples of the misuse of digital content include violating copyrights of the content and tampering with important material such as contents of video surveillance. In this paper we present an algorithm that extracts a binary signature from an image. This approach can be used to search for possible copyright violations by finding images with signatures close to that of a given image. The experimental results show that the algorithm can be very effective in helping users to retrieve sets of almost identical images from large collections of images. The signature can also be used for tamper detection. We will show that the signatures we extract are immune to quantization errors that result from compression and decompression.

UR - http://www.scopus.com/inward/record.url?scp=0033319097&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0033319097&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0033319097

VL - 3845

SP - 22

EP - 28

BT - Proceedings of SPIE - The International Society for Optical Engineering

PB - Society of Photo-Optical Instrumentation Engineers

ER -