通过噪声分析检测图像修补伪造，效果优于现有方法。
Enhanced Wavelet Scattering Network for image inpainting detection
- 结合双树复小波与卷积网络提取特征并定位伪造区域
- 在多个数据集上准确率超主流方法，最高达98.7%
- 适合数字取证、图像安全领域研究人员参考
图像修补工具的快速发展使数字图像篡改变得极为便捷。本文提出一种基于低层噪声分析的图像修补伪造检测方法，融合双树复小波变换（DT-CWT）进行特征提取，配合卷积神经网络（CNN）实现伪造区域的检测与定位，并引入纹理分割与噪声方差估计的创新融合模块以提升精度。DT-CWT具备平移不变性与方向选择性，能有效捕捉修补过程中引入的微弱频域与方向性异常。实验对比了多种神经网络架构，最终验证了所提方法在多个公开数据集上的优越性能，显著优于现有先进方法。训练代码及预训练模型权重将开源于https://github.com/jmaba/Deep-dual-tree-complex-neural-network-for-image-inpainting-detection。
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。