Detectify : Image Tampering Detection using Error Level Analysis (ELA) and Convolutional Neural Network (CNN)

In the evolving digital landscape, the proliferation of manipulated images poses a significant challenge to the authenticity and integrity of visual content. This project investigates cutting-edge image manipulation detection techniques, employing a combination of Error Level Analysis (ELA) and Convolutional Neural Networks (CNN) for robust prediction. Focusing on the widely-used CASIA V2.0 dataset, the study provides a comprehensive evaluation of image manipulation methods. Error Level Analysis is utilized as a forensic tool to identify alterations in the compression levels of manipulated images. By scrutinizing variations in error levels, the project aims to enhance the detection accuracy of manipulated regions within visual content. The CNN model is meticulously crafted and trained using preprocessed ELA images to acquire nuanced features essential for discerning tampering- induced alterations. The proposed hybrid approach, integrating ELA and CNN, establishes a robust framework for detecting image manipulation that is adaptable and efficient. Through the meticulous examination of the CASIA V2.0 dataset, this project contributes to ongoing efforts in combating digital image manipulation. This study serves as a valuable resource for forensic analysts, researchers, and practitioners working towards ensuring the veracity of digital images, offering a nuanced understanding of image manipulation techniques in the contemporary digital era.