Geometric rectification‐based neural network architecture for image manipulation detection

Abstract

Determination of image authenticity usually requires the identification and localization of the manipulated regions of images. Hence, image manipulation detection has become one of the most important tasks in the field of multimedia forensics. Recently, Convolutional Neural Networks (CNNs) have achieved promising performance in image manipulation detection. However, it is hard for the existing CNN-based manipulation detection approaches to accurately identify and localize the manipulated regions that have undergone geometric transformations, since CNNs are limited by their inability to be geometrically invariant. To address this issue, we propose a geometric rectification-based neural network architecture for image manipulation detection. In this type of network architecture, following the detection of a set of potential manipulated regions (PMRs) using Region Proposal Network, the Spatial Transformer Network is employed to geometrically rectify the convolutional feature maps (CFMs) of these regions to obtain the geometrically rectified CFMs (GR-CFMs). Subsequently, the residual feature maps (RFMs) are computed to capture the characteristic inconsistency between the CFMs and GR-CFMs of each PMR. Finally, the computed RFMs are automatically integrated with the GR-CFMs by a designed attention module to determine whether each PMR is a Grant/Award Numbers: MOST 108-2221-E-259-009-MY2, 109-2221-E-259-010 manipulated region and to localize the manipulated part at the pixel-level. Extensive experiments on the public data set as well as on our challenging data set demonstrate that the proposed network architecture achieves desirable performance in identifying and localizing regions with common tampering artifacts, which involve geometric transformations.

Document images forgery localization using a two‐stream network

“…As any type of content‐changing forgery methods will directly alter the spatial information of document image, spatial information plays an important role in capturing forgery traces. Many previous image forgery localization methods also attempt to capture forgery traces from spatial information 1,4,5,39,40 . As the in‐depth development of deep learning in image forensics, there are many deep neural networks (e.g., Faster R‐CNN, 5 LSTM, 1 Inception, 7 and VGG 3 ).…”

“…Many previous image forgery localization methods also attempt to capture forgery traces from spatial information. 1,4,5,39,40 As the in-depth development of deep learning in image forensics, there are many deep neural networks (e.g., Faster R-CNN, 5 LSTM, 1 Inception, 7 and VGG 3 ). In this paper, we design an SIEN base on Inception 41 to extract features in spatial information.…”

A neural autonomous robotic manipulator with three degrees of freedom

“…Due to their flexibility, ANNs can be used in different applications, such as universal function approximator, process control and robotics, 26,27 pattern classifier, [28][29][30] time series prediction, function optimization, computer vision, 31 large-scale global optimization, 32 image authenticity verification, 33 time-varying quadratic programming, 34 and image improvement and restoration. 35 Other alternative techniques for image improvement and reconstruction have also stood out in the scientific community, as can be seen in the works [36][37][38].…”

MC‐Net: Learning mutually‐complementary features for image manipulation localization

“…Pun et al 30 took the contextual super‐pixel blocks to assist the classification of the blocks. Furthermore, a line of research focuses on image manipulation localization , which aims to localize the tampered regions 31–33 …”

“…Furthermore, a line of research focuses on image manipulation localization, which aims to localize the tampered regions. [31][32][33] The core hypothesis of the image manipulation localization methods is that any of the manipulation operations would leave some abnormal traces. [34][35][36][37] Some localization methods capture the manipulation anomalies by using manually constructed features, such as resampling, 37 noise, 38 edge, 39,40 and so forth.…”