Fake region identification in an image using deep learning segmentation model

A forged image is a major source of counterfeit news and is mostly used in a spiteful manner such as exciting targeted mob, identity theft, defaming individual, or misleading law bodies. Therefore, a technique is required to detect the tampered regions in a forged image. Deep learning is surpassing technology for prediction or classification tasks in images. Challenges in this technology are a variety of datasets to train the model and specific architecture for a specific application. In this paper, a deep learning model is extended for the localization of tampered regions in a forged image. This is an extension of the well-known U-Net segmentation model. In the proposed model, batch normalization layers and identity-blocks are placed at suitable places of the U-Net model to overcome the challenges such as overfitting and loss of information during max-pooling. To overcome the challenge of the dataset five different publicly available datasets are taken to train, validate and test the model. The trained model is also tested on four created forged images (not belong to the dataset) whose acquisition sources may different i.e. medical image, identity document, natural image, and scanned report. The result of the proposed model is compared with state-of-the-art techniques which show that the method works better than others.

Automated summary

This paper presents a method using deep learning to locate tampered regions in forged images. By extending the U-Net segmentation model and adding batch normalization layers and identity-blocks, the challenges of overfitting and information loss are addressed. The proposed model is trained on five different publicly available datasets and tested on four created forged images, showing better performance compared to state-of-the-art techniques.