# Image Forgery Localization Based on Multi-Scale Convolutional Neural Networks

## TL;DR

This paper introduces a multi-scale CNN approach combined with segmentation techniques to improve the accuracy of digital image forgery localization, demonstrating significant performance gains through extensive experiments.

## Contribution

The paper presents a novel multi-scale CNN framework with segmentation-based fusion for enhanced image forgery localization, integrating small and large-scale analysis.

## Key findings

- Effective localization of tampered regions in images.
- Significant performance improvement over existing methods.
- Robustness across various tampering scenarios.

## Abstract

In this paper, we propose to utilize Convolutional Neural Networks (CNNs) and the segmentation-based multi-scale analysis to locate tampered areas in digital images. First, to deal with color input sliding windows of different scales, a unified CNN architecture is designed. Then, we elaborately design the training procedures of CNNs on sampled training patches. With a set of robust multi-scale tampering detectors based on CNNs, complementary tampering possibility maps can be generated. Last but not least, a segmentation-based method is proposed to fuse the maps and generate the final decision map. By exploiting the benefits of both the small-scale and large-scale analyses, the segmentation-based multi-scale analysis can lead to a performance leap in forgery localization of CNNs. Numerous experiments are conducted to demonstrate the effectiveness and efficiency of our method.