Multiscale Attention Network for Detection and Localization of Image Splicing Forgery

Image forgery detection and localization have become a research topic of increasing interest with the enormous spread of manipulated images on the web. Most previous methods related to image forgery focus on one particular attribute or neglect the importance of multiscale information. Such approaches are considered not suitable for detecting and locating multiscale splicing forgeries. This article presents a novel approach that exploits residual attention and integrates multiscale local and global information to improve detection accuracy. In the proposed method, we first aggregate multilevel convolutional feature maps extracted by the encoder to enrich the feature representations and improve the ability of the model to locate multiscale forged areas. Then, we design a residual attention block (RAB) to purify the features, which enhances the response of task-related regions and suppresses noise information. Furthermore, a global feature mining block (GFMB) is proposed to capture the long-range dependencies between different regions of the image, enabling the model to handle complex tampering scenarios effectively. The multiscale splicing forgery regions are precisely detected and located by utilizing the proposed method. The extensive experiments are conducted on three benchmark datasets, CASIA, COLUMB, and NIST'16. Specifically, our model achieves the F1 score of 84.3%, 87.9%, and 80.8% on CASIA, COLUMB, and NIST'16 test sets, respectively, outperforming state-of-the-art methods.