Learning Feature Disentanglement and Dynamic Fusion for Recaptured Image Forensic

TL;DR

This paper introduces a novel model and a large-scale real-scene dataset for recaptured image forensic analysis, enabling recognition of multiple recapture patterns with improved accuracy.

Contribution

The paper presents a new Feature Disentanglement and Dynamic Fusion (FDDF) model and the first large-scale real-scene dataset for comprehensive recaptured image forensic recognition.

Findings

FDDF achieves state-of-the-art performance on RUR dataset.

The RUR dataset is five times larger than previous datasets.

The model effectively recognizes multiple recapture patterns.

Abstract

Image recapture seriously breaks the fairness of artificial intelligent (AI) systems, which deceives the system by recapturing others' images. Most of the existing recapture models can only address a single pattern of recapture (e.g., moire, edge, artifact, and others) based on the datasets with simulated recaptured images using fixed electronic devices. In this paper, we explicitly redefine image recapture forensic task as four patterns of image recapture recognition, i.e., moire recapture, edge recapture, artifact recapture, and other recapture. Meanwhile, we propose a novel Feature Disentanglement and Dynamic Fusion (FDDF) model to adaptively learn the most effective recapture feature representation for covering different recapture pattern recognition. Furthermore, we collect a large-scale Real-scene Universal Recapture (RUR) dataset containing various recapture patterns, which is about five times the number of previously published datasets. To the best of our knowledge, we are the first to propose a general model and a general real-scene large-scale dataset for recaptured image forensic. Extensive experiments show that our proposed FDDF can achieve state-of-the-art performance on the RUR dataset.