An automatic enhanced filters with frequency‑based copy‑move forgery detection for social media images

Mat Abir, Noor Atikah and Abd Warif, Nor Bakiah and Zainal, Nurezayana (2024) An automatic enhanced filters with frequency‑based copy‑move forgery detection for social media images. Multimedia Tools and Applications, 83. pp. 1513-1538.

Text J16830_ace79442b2806b9e1a87ff70f440aaad.pdf Restricted to Registered users only Download (2MB) | Request a copy

Abstract

Using images in various fle types has become common in the modern digital world, such as social media posts, research reports, and legal documents. The availability of low-cost image manipulation tools has made it easier to change images, potentially leading to undetected image fraud. One such form of image manipulation is copy-move forgery (CMF), which is difcult to detect due to the similarities in image features. There have been eforts to detect CMF using copy-move forgery detection (CMFD) methods. However, most research has focused on CMF images with attacks rather than social media. Social media has contributed signifcantly to the image manipulation phenomenon, and additional postprocessing techniques on social media platforms have afected the efciency of the CMFD methods. Therefore, this research proposes a two-stage pre-processing phase combined with frequency-based CMFD to detect CMF images in diferent social media platforms. The frst stage includes automatic image selection, followed by image enhancement with flters to improve image quality. The experimental results show that the proposed method achieves the highest detection score compared to existing CMFD methods, with an average score of 90% for CMF-Facebook, 91% for CMF-WhatsApp, and 85% for CMF-Twitter. This research highlights the importance of developing solutions to detect image forgery in social media and the potential of combining pre-processing with frequency-based methods to improve results.

Item Type:	Article
Uncontrolled Keywords:	Digital images · Copy-move forgery (CMF) · Copy-move forgery detection (CMFD) · Social media
Subjects:	Q Science > QA Mathematics > QA71-90 Instruments and machines
Depositing User:	Mr. Mohamad Zulkhibri Rahmad
Date Deposited:	17 Nov 2024 03:07
Last Modified:	17 Nov 2024 03:18
URI:	http://eprints.uthm.edu.my/id/eprint/11690

Actions (login required)

View Item