Image Counterfeiting Detection and Localization Using Deep Learning Algorithms

Abstract

As social networking services such as Whatsapp, Facebook, Twitter, and Instagram have grown in popularity over the past two decades, the volume of picture data created throughout the globe has exploded. Images that have been altered or doctored using editing software such as Adobe Photoshop, GIMP, and Paint-3D are a major source of concern in the digital age. As a result, it is essential to verify the validity of suspect images before taking action against people who fabricate them. Copy-move forgery and spliced image fraud are two of the most extensively used picture forgery methods in the field. Recent Deep Learning (DL) algorithms have simplified tasks like categorization, localization, segmentation, and other comparable studies. With the use of Residual Neural Networks (ResNet), copy-move forgery and spliced fraud in photographs may be discovered and classified. Experimental results on benchmark datasets such as CASIA-2, MICC-F2000, and CoMoFoD indicate significant gains over state-of-the-art approaches. Gradient Class activation mappings (Grad-CAM) were applied to find forged regions in tampered photographs, and the suggested approach was also proven to be successful in predicting tampered images. On the CoMoFoD dataset, a classification accuracy of 99.9% was attained, while on the MICC-F 2000 dataset, it was 97%.