Image manipulation detection with Binary Similarity Measures

Sevinç Bayram, Ismail Avcibaş, Bülent Sankur, Nasir Memon

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

Abstract

Since extremely powerful technologies are now available to generate and process digital images, there is a concomitant need for developing techniques to distinguish the original images from the altered ones, the genuine ones from the doctored ones. In this paper we focus on this problem and propose a method based on the neighbor bit planes of the image. The basic idea is that, the correlation between the bit planes as well the binary texture characteristics within the bit planes will differ between an original and a doctored image. This change in the intrinsic characteristics of the image can be monitored via the quantal-spatial moments of the bit planes. These so-called Binary Similarity Measures are used as features in classifier design. It has been shown that the linear classifiers based on BSM features can detect with satisfactory reliability most of the image doctoring executed via Photoshop tool.

Original languageEnglish (US)
Title of host publication13th European Signal Processing Conference, EUSIPCO 2005
Pages2139-2142
Number of pages4
StatePublished - Dec 1 2005
Event13th European Signal Processing Conference, EUSIPCO 2005 - Antalya, Turkey
Duration: Sep 4 2005Sep 8 2005

Publication series

Name13th European Signal Processing Conference, EUSIPCO 2005

Other

Other13th European Signal Processing Conference, EUSIPCO 2005
CountryTurkey
CityAntalya
Period9/4/059/8/05

    Fingerprint

Keywords

  • Binarysimilarity measures
  • Classification
  • Digital image forensics
  • Image processing

ASJC Scopus subject areas

  • Signal Processing

Cite this

Bayram, S., Avcibaş, I., Sankur, B., & Memon, N. (2005). Image manipulation detection with Binary Similarity Measures. In 13th European Signal Processing Conference, EUSIPCO 2005 (pp. 2139-2142). (13th European Signal Processing Conference, EUSIPCO 2005).