A Serial Image Copy-Move Forgery Localization Scheme With Source/Target Distinguishment

• Published in: IEEE transactions on multimedia Vol. 23; pp. 3506 - 3517
• Main Authors: Chen, Beijing, Tan, Weijin, Coatrieux, Gouenou, Zheng, Yuhui, Shi, Yun-Qing
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Artificial neural networks; atrous convolution; attention mechanism; Convolution; Copy-move; Correlation; Datasets; Decoding; deep neural network; Feature extraction; Forgery; image forgery; Localization; Similarity; Target detection; Task analysis
• DOI: 10.1109/TMM.2020.3026868
• ISSN: 1520-9210

In this paper, we improve the parallel deep neural network (DNN) scheme BusterNet for image copy-move forgery localization with source/target region distinguishment. BusterNet is based on two branches, i.e., Simi-Det and Mani-Det, and suffers from two main drawbacks: (a) it should ensure that both branches correctly locate regions; (b) the Simi-Det branch only extracts single-level and low-resolution features using VGG16 with four pooling layers. To ensure the identification of the source and target regions, we introduce two subnetworks that are constructed serially: the copy-move similarity detection network (CMSDNet) and the source/target region distinguishment network (STRDNet). Regarding the second drawback, the CMSDNet subnetwork improves Simi-Det by removing the last pooling layer in VGG16 and by introducing atrous convolution into VGG16 to preserve field-of-views of filters after the removal of the fourth pooling layer; double-level self-correlation is also considered for matching hierarchical features. Moreover, atrous spatial pyramid pooling and attention mechanism allow the capture of multiscale features and provide evidence for important information. Finally, STRDNet is designed to determine the similar regions obtained from CMSDNet directly as tampered regions and untampered regions. It determines regions at the image-level rather than at the pixel-level as made by Mani-Det of BusterNet. Experimental results on four publicly available datasets (new synthetic dataset, CASIA, CoMoFoD, and COVERAGE) demonstrate that the proposed algorithm is superior to the state-of-the-art algorithms in terms of similarity detection ability and source/target distinguishment ability.