Paper Contents
Abstract
The increasing abuse of image editing software causesthe authenticity of digital images questionable. The widespread availability of online social networks(OSNs) makes them the dominant channels for transmittingforged images to report fake news. The last decade hasseen lot of research advancement in the area of digitalimage forensics, where the investigation for possibleforgeries is based on post-processing of images. Deeplearning approaches have shown promising results invarious image classification problems but cannot findhidden patterns in digital images, which can reliablydetect image forgeries. The objective of the proposedapproach is to detection the accuracy. In addition toanalyze the schemes and evaluate and compare their performances in terms of a proposed set of parameters, which may be used as a standard benchmark for evaluating the efficiency of any general copy-moveforgery detection technique for digital images. Wefurther incorporate the tailored noise into a robusttraining framework, significantly improving therobustness of the image forgery detector. The comparisonresults provided by them would help a user to select the most optimal forgery detection technique, depending onthe author requirements. This paper discuses variousforgery detection in social media images and suggests new idea of detection.
Copyright
Copyright © 2023 Tejaswini surve KS. This is an open access article distributed under the Creative Commons Attribution License.
