摘要
This paper introduces a machine learning based copy-move forgery (CMF) localization method. The basic convolutional neural network cannot be applied to CMF detection because CMF frequently involves rotation transformation. Therefore, we propose a rotation-invariant feature based on the root-mean squared energy using high-frequency wavelet coefficients. Instead of using three color image channels, two-scale energy features and low-frequency subband image are fed into the conventional VGG16 network. A correlation module is used by employing small feature patches generated by the VGG16 network to obtain the possible copied and moved patch pairs. The all-to-all similarity score is computed using the correlation module. To generate the final binary localization map, a simplified mask decoder module is introduced, which is composed of two simple bilinear upsampling and two batch-normalized-inception-based mask deconvolution followed by bilinear upsampling. We perform experiments on four test datasets and compare the proposed method with state-of-the-art tampering localization methods. The results demonstrate that the proposed scheme outperforms the existing approaches.
学科与关键词
- An efficient method for image forgery detection based on trigonometric transforms and deep learningAl Azrak, Faten Maher; Sedik, Ahmed; Dessowky, Moawad I.; El Banby, Ghada M.; Khalaf, Ashraf A. M.; Elkorany, Ahmed S.; Abd El-Samie, Fathi E.*MULTIMEDIA TOOLS AND APPLICATIONS, 2020, 79(25-26): 18221-18243.被引 32
- Image copy-move forgery passive detection based on improved PCNN and self-selected sub-imagesZhou, Guoshuai; Tian, Xiuxia*; Zhou, AoyingFrontiers of Computer Science, 2022, 16(4): 164705.被引 5
- An approach for copy-move image multiple forgery detection based on an optimized pre-trained deep learning modelChaitra, B.*; Reddy, P. V. BhaskarKnowledge-Based Systems, 2023, 269: 110508.被引 5
