Title: A robust passive blind copy-move image forgery detection
Authors: Jayashree D. Gavade; S.R. Chougule; Vishwaja Rathod
Addresses: Department of Electronics, DKTE's Textile and Engineering Institute, Ichalakranji, Maharashtra, India ' Department of Electronics and Tele-Communication, KIT's College of Engineering, Kolhapur, Maharashtra, India ' Department of Electronics, DKTE's Textile and Engineering Institute, Ichalakranji, Maharashtra, India
Abstract: Image forensic is the important research area which deals to verify the authenticity of the digital image. Copy-move forgery is common type of forgery used to modify the image. This paper proposes passive blind forensic copy-move forgery detection technique. The combination of dyadic wavelet transform (DyWT) and scale invariant feature transform (SIFT) is used. Finally, RANSAC is used to improve the detection accuracy. The performance of the algorithm is verified with 45 original/forged images considering various attacks, such as scaling, rotation, small object and multiple copy-move pasting. The experimental results reveal that the proposed technique identifies and locates the forged area accurately for all attacks. The comparison of the proposed method is done with existing methods in terms of detection accuracy, recall, and precision. The simulation results show that for the most of the cases the proposed method outperforms the existing methods.
Keywords: image forensic; copy-move forgery; scale invariant feature transform; SIFT; dyadic wavelet transform; DyWT; DWT; RANSAC; detection accuracy; recall; precision.
DOI: 10.1504/IJICS.2021.114707
International Journal of Information and Computer Security, 2021 Vol.14 No.3/4, pp.300 - 317
Received: 23 Apr 2018
Accepted: 25 Jul 2018
Published online: 04 May 2021 *