Abstract
Due to the wide availability of the tools used to produce manipulated images, a large number of digital images have been tampered with in various media, such as newspapers and social networks, which makes the detection of tampered images particularly important. Therefore, an image manipulation detection algorithm leveraged by the Faster Region-based Convolutional Neural Network (Faster R-CNN) model combined with edge detection was proposed in this paper. In our algorithm, first, original tampered images and their detected edges were sent into symmetrical ResNet101 networks to extract tampering features. Then, these features were put into the Region of Interest (RoI) pooling layer. Instead of the RoI max pooling approach, the bilinear interpolation method was adopted to obtain the RoI region. After the RoI features of original input images and edge feature images were sent into bilinear pooling layer for feature fusion, tampering classification was performed in fully connection layer. Finally, Region Proposal Network (RPN) was used to locate forgery regions. Experimental results on three different image manipulation datasets show that our proposed algorithm can detect tampered images more effectively than other existing image manipulation detection algorithms.
Highlights
In modern society, image editing is becoming increasingly popular
[16], we develop an image manipulation detection algorithm image based leveraging architecture and Faster R-Convolutional Neural Network (CNN)
Compared with the Faster R-CNN model, our algorithm adds an edge detection layer, finds inconsistency between tampered and non-tampered areas, removes Region of Interest (RoI) max pooling, uses bilinear interpolation method to fix the size of the interest area, avoids only extracting high-frequency information, and improves image tampering detection performance
Summary
Image editing is becoming increasingly popular. With the simplification of image editing software, images can be edited even on one mobile phone. Passive forensics algorithms, known as image manipulation detection methods, are studied in this focuses onon certain features of this paper. Several new algorithms using deep learning weremodel proposed improve manipulation image splicing and CMF. Neural Network (Faster a two-stream image manipulation developed to Convolutional detect image forgery by learning theR-CNN). Addition, itto mainly to detect target image manipulation detectionfor model [16] wasIndeveloped detectaims different types of tampering, tampered while ignoring background tampering It has modest detection performance for CMF images. Compared with the Faster R-CNN model, our algorithm adds an edge detection layer, finds inconsistency between tampered and non-tampered areas, removes RoI max pooling, uses bilinear interpolation method to fix the size of the interest area, avoids only extracting high-frequency information, and improves image tampering detection performance. Experimental results show that our method is more accurate than the original max pooling approach in image manipulation detection
Sign-in/Register to view highlights & summary 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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
