Abstract
Exemplar-based image inpainting technology is a “double-edged sword”. It can not only restore the integrity of image by inpainting damaged or removed regions, but can also tamper with the image by using the pixels around the object region to fill in the gaps left by object removal. Through the research and analysis, it is found that the existing exemplar-based image inpainting forensics methods generally have the following disadvantages: the abnormal similar patches are time-consuming and inaccurate to search, have a high false alarm rate and a lack of robustness to multiple post-processing combined operations. In view of the above shortcomings, a detection method based on long short-term memory (LSTM)-convolutional neural network (CNN) for image object removal is proposed. In this method, CNN is used to search for abnormal similar patches. Because of CNN’s strong learning ability, it improves the speed and accuracy of the search. The LSTM network is used to eliminate the influence of false alarm patches on detection results and reduce the false alarm rate. A filtering module is designed to eliminate the attack of post-processing operation. Experimental results show that the method has a high accuracy, and can resist the attack of post-processing combination operations. It can achieve a better performance than the state-of-the-art approaches.
Highlights
In order to make up for the shortcomings of existing methods in the images inpainting forensics, reveal the image inpainting with post-processing attacks, this paper proposes an image inpainting forensics method based on long short-term memory (LSTM)-convolutional neural network (CNN), which uses a convolutional neural network (CNN) to identify suspicious similar patches in the tampered image, and exploits LSTM to distinguish the texture consistent regions from suspicious regions, so as to greatly reduce the false alarm rate
We present a CNN based nearest neighbor image patch matching algorithm to quickly search for abnormal similar patches in images; We design a false alarm removal module based on the CNN and LSTM network
In order to belongs to lossy compression, which will inevitably destroy the correlation of discrete cosine transform make CNN focus more on learning the trace features introduced by image tampering and reduce the (DCT) coefficients among pixels and other statistical features
Summary
Beijing Key Lab of Intelligent Telecommunication Software and Multimedia, Beijing University of Posts and Telecommunications, Beijing 100876, China.
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
