Copy-move forgery detection based on convolutional kernel network

Abstract

In this paper, a copy-move forgery detection method based on Convolutional Kernel Network is proposed. Different from methods based on conventional hand-crafted features, Convolutional Kernel Network is a kind of data-driven local descriptor with the deep convolutional structure. Thanks to the development of deep learning theories and widely available datasets, the data-driven methods can achieve competitive performance on different conditions for its excellent discriminative capability. Besides, our Convolutional Kernel Network is reformulated as a series of matrix computations and convolutional operations which are easy to parallelize and accelerate by GPU, leading to high efficiency. Then, appropriate preprocessing and postprocessing for Convolutional Kernel Network are adopted to achieve copy-move forgery detection. Particularly, a segmentation-based keypoints distribution strategy is proposed and a GPU-based adaptive oversegmentation method is adopted. Numerous experiments are conducted to demonstrate the effectiveness and robustness of the GPU version of Convolutional Kernel Network, and the stateof-the-art performance of the proposed copy-move forgery detection method based on Convolutional Kernel Network.

Detection Copy-Move Forgery in Image Via Quaternion Polar Harmonic Transforms

“…The detection performance of the proposed CMFD is compared with that of the state-ofthe-art techniques in literature that used the same CoMoFoD dataset and validation metrics to achieve fair comparison. Table 8 presents a comparison of the proposed approach with other popular approaches, namely, HOG [3], HOGM [39], PCET [40], LGWP [41] and Convolutional Kernel Network [42]. The proposed CMFD based on QPCET descriptors provide superior detection efficiency to previous methods.…”

“…Therefore, the performance of any forgery detection scheme with block matching method fundamentally depends on the invariant features used to extract block features and the method used to find the similar block features. [41] LGWP CDR 0.961 0.973 n/a 0.714 n/a 0.501 n/a FDR n/a n/a n/a n/a Liu, Guan, & Zhao [42] Convolutional Kernel Network CDR 0.827 0.784 0.844 0.726 0.781 0.900 0.751 FDR n/a n/a n/a n/a n/a n/a n/a The overall test results indicate that our proposed approach can obtain effective detection results for CMF of colour images under various challenging conditions. The results for simple CMF reveal that the performance of the proposed method is nearly complete and flawless with a nearly perfect CDR and an FDR that is decreased to nil in all categories.…”

A Survey on Digital Image Copy-Move Forgery Localization Using Passive Techniques

“…Instead, they learn the related features automatically during the network training stage [Liu and Pun (2018)]. So, some deep learning-based methods [Liu, Guan and Zhao (2018); Wu, Abd-Almageed and Natarajan (2018)] have been proposed. More specifically, Liu et al [Liu, Guan and Zhao (2018)] decomposed an image adaptively using Convolutional Oriented Boundaries (COB) algorithm.…”

Copy-Move Forgery Detection in Digital Images using Neural Network

“…In [16], the authors introduced a new end-to-end deep neural network, which was robust against several assaults. Meanwhile, in [17], the authors utilized deep neural network for extracting features on behalf of the copy-move forgery identification. Later, in [18], authors used a DNN-based patch classifier for the recognition of counterfeited regions.…”