Abstract
Digital image forgery is a growing problem due to the increase in readily-available technology that makes the process relatively easy. In response, several approaches have been developed for detecting digital forgeries. This paper proposes a novel scheme based on neural networks and deep learning, focusing on the convolutional neural network (CNN) architecture approach to enhance a copy-move forgery detection. The proposed approach employs a CNN architecture that incorporates pre-processing layers to give satisfactory results. In addition, the possibility of using this model for various copy-move forgery techniques is explained. The experiments show that the overall validation accuracy is 90%, with a set iteration limit.
Highlights
Digital editing is becoming less and less complicated with time, as a result of the increased availability of a wide array of digital image editing tools
Because the image analysis and computer vision in the CNN strategy are so highly advanced, CNN generally provides excellent performance [9,10] in image forgery detection, through the composition of simplistic non-linear and linear filtering operations [11]. This present paper proposes a novel approach for image forgery detection and localization which is based on scale variant convolutional neural networks (SVCNNs)
In [14,15,16] deep learning methods applied to computer vision problems resulted in a local convolution feature data-driven CNN, while in other research, copy-move forgery detection algorithms were mostly based on computer vision tasks such as image retrieval [17,18], classification [19], and object detection [20]
Summary
Digital editing is becoming less and less complicated with time, as a result of the increased availability of a wide array of digital image editing tools. Symmetry 2019, 11, 1280 three neural networks, CNNs are most commonly used in vision applications These approaches employ local neighborhood pooling operations and trainable filters when testing raw input images, thereby creating hierarchies (from concrete to abstract) of the features under examination. Because the image analysis and computer vision in the CNN strategy are so highly advanced, CNN generally provides excellent performance [9,10] in image forgery detection, through the composition of simplistic non-linear and linear filtering operations (e.g., rectification and convolution) [11] This present paper proposes a novel approach for image forgery detection and localization which is based on scale variant convolutional neural networks (SVCNNs).
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
