Abstract
ABSTRACT Copy-move forgery (CMF) is a variety of image faking in which parts of an image are duplicated and added inside the same image. Up to now, many applications have been proposed to expose this type of forgery. These algorithms were developed to detect suspicious images containing CMF. However, when attacks such as compression and noise addition are applied to the image in such forgery operations, CMF detection (CMFD) approaches have difficulty in recognizing the fake images. This study presents a keypoint-based CMFD approach that performs well under various post-transaction changes. This is achieved by extracting scale-invariant feature transform (SIFT) and KAZE features using the colour channels in the HSV colour space instead of greyscale images. After the SIFT and KAZE descriptors have been extracted from each colour channel, they are combined to form the feature that is used in the matching step to detect similar regions. Thus, the proposed CMFD approach is more effective because stronger features are obtained when they are combined. The test findings on the Image Manipulation Dataset (IMD) demonstrated that our technique had successfully identified CMF under a variety of post-transaction alterations.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: 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.