DMobile-ELA: Digital Image Forgery Detection via cascaded Atrous MobileNet and Error Level Analysis

Abstract

With the current developments in technology, not only has digital media become widely available, the editing and manipulation of digital media has become equally available to everyone without any prior experience. The need for detecting manipulated images has grown immensely as it can now cause false information in news media, forensics, and daily life of common users. In this work, a cascaded approach DMobile-ELA is presented to ensure an image's credibility and that the data it contains has not been compromised. DMobile-ELA integrates Error Level Analysis and MobileNet-based classification for tampering detection. It was able to achieve promising results compared to the state of the art on CASIAv2.0 dataset. DMobile-ELA has successfully reached a training accuracy of 99.79% and a validation accuracy of 98.48% in detecting image manipulation.