WCSE

Image Tampering Localization Based on Pyramid Multi-scale Pooling Module

Abstract— In this paper, we proposed a new two-stream image forgery localization method based on pyramid multi-scale pooling module. One stream learns the differences in JPEG compression rate between original regions and tampered regions by processed through ELA. In the second stream, the network learns the global image manipulation features from the input image RGB values. Next the fusion stage fuses multiple tampering features from the dual-channel feature extraction network to generate the shallow feature map, Coordinate Attention is applied to refine the predicted mask and further improve the localization accuracy. And then through the multi-scale pyramid pooling module, so the secondary fusion is carried out. Finally, the fused feature map restores the original image size by using UpSampling for Pixel level classification prediction. The proposed net can effectively decrease incorrect prediction since it makes better use of the contextual spatial information in images. And most of all, from two stages extraction fuses lowlevel and high-level information to refine the global manipulation features. The experimental results on several public datasets show that the proposed model outperforms some state-of-the-art methods.

Index Terms— Forgery Localization, Pyramid Multi-Scale Pooling, Feature Fusion, Coordinate Attention, Pixel-level Classification Prediction.

Caixia Meng
School of Computer Science and Technology, Xi'an University of Posts and Telecommunications; Shannxi Key Laboratory of Network Data Analysis and Intelligent Processing, China; Xi’an Key Laboratory of Big Data and Intelligent Computing, China
Bing Zhao
School of Computer Science and Technology, Xi'an University of Posts and Telecommunications; Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing, China
Kaijie Xi
School of Computer Science and Technology, Xi'an University of Posts and Telecommunications
Jiabao Zhang
School of Computer Science and Technology, Xi'an University of Posts and Telecommunications
Hongpeng Chu
School of Computer Science and Technology, Xi'an University of Posts and Telecommunications

[Download]

Cite: Caixia Meng, Bing Zhao, Kaijie Xi, Jiabao Zhang, Hongpeng Chu, "Image Tampering Localization Based on Pyramid Multi-scale Pooling Module," WCSE 2022 Spring Event: 2022 9th International Conference on Industrial Engineering and Applications, pp. 72-80, Sanya, China, April 15-18, 2022.