Enhanced Wavelet Scattering Network for image inpainting detection

TL;DR

This paper introduces an enhanced wavelet scattering network combining DT-CWT and CNNs for improved detection and localization of image inpainting forgeries, outperforming existing methods.

Contribution

It proposes a novel fusion of DT-CWT features with CNNs and texture analysis for more accurate inpainting forgery detection and localization.

Findings

Superior detection accuracy over state-of-the-art methods

Effective localization of forged regions

Robustness against subtle inpainting artifacts

Abstract

The rapid advancement of image inpainting tools, especially those aimed at removing artifacts, has made digital image manipulation alarmingly accessible. This paper proposes several innovative ideas for detecting inpainting forgeries based on low level noise analysis by combining Dual-Tree Complex Wavelet Transform (DT-CWT) for feature extraction with convolutional neural networks (CNN) for forged area detection and localization, and lastly by employing an innovative combination of texture segmentation with noise variance estimations. The DT-CWT offers significant advantages due to its shift-invariance, enhancing its robustness against subtle manipulations during the inpainting process. Furthermore, its directional selectivity allows for the detection of subtle artifacts introduced by inpainting within specific frequency bands and orientations. Various neural network architectures were evaluated and proposed. Lastly, we propose a fusion detection module that combines texture analysis with noise variance estimation to give the forged area. Our approach was benchmarked against state-of-the-art methods and demonstrated superior performance over all cited alternatives. The training code (with pretrained model weights) as long as the dataset will be available at https://github.com/jmaba/Deep-dual-tree-complex-neural-network-for-image-inpainting-detection