Detection of Image Tampering Using Deep Learning, Error Levels & Noise Residuals

Abstract

Abstract Images once were considered as a reliable source of information. However, when photo-editing software started to get noticed it gave rise to illegal activities that is called image tampering. These days we can came across innumerable tampered images across the internet. Software such as Photoshop, GNU Image Manipulation Program, etc. are applied to form tampered images from real ones in just a few minutes. When it comes to discover hidden signs of tampering in an image deep learning models are far more effective than any other methods. Models used in deep learning are capable of extracting intricate features from an image automatically. To differentiate between authentic and tampered images we presented a dual-branch Convolutional Neural Network (CNN) in conjunction with Error Level Analysis (ELA) and noise residuals from Spatial Rich Model (SRM). For our experiment we utilized the freely accessible CASIA dataset. After training the dual-branch network for 16 epochs, it generated an accuracy of 98.55%. We have also provided a comparative analysis with other previously proposed work in the field of image forgery detection. This experiment is done to prove that deep learning models along with some well known traditional approaches can provide better results for detecting tampered images.