Detection of Tool based Edited Images from Error Level Analysis and Convolutional Neural Network

TL;DR

This paper proposes a method combining Error Level Analysis and Convolutional Neural Networks to detect images tampered with editing tools, evaluated on the CASIA ITDE v2 dataset with promising accuracy.

Contribution

It introduces a novel approach integrating Error Level Analysis with CNNs for improved detection of edited images.

Findings

Achieved high accuracy on CASIA ITDE v2 dataset

Demonstrated effectiveness with 50 and 100 training epochs

Validated approach through training and validation graphs

Abstract

Image Forgery is a problem of image forensics and its detection can be leveraged using Deep Learning. In this paper we present an approach for identification of authentic and tampered images done using image editing tools with Error Level Analysis and Convolutional Neural Network. The process is performed on CASIA ITDE v2 dataset and trained for 50 and 100 epochs respectively. The respective accuracies of the training and validation sets are represented using graphs.