RETRACTED ARTICLE: A survey on copy-move image forgery detection based on deep-learning techniques

The widespread use of digital images on social media and the internet has led to increased image forgery, which poses a significant challenge to their authenticity. It is crucial to validate the integrity of images in this digital era, where they are widely used for communication and information. This survey comprehensively reviews the existing digital image forgery detection techniques, focusing on copy-move forgery. Copy-move forgery is a common image tampering technique where a part of the image is duplicated and pasted elsewhere in the same image. Detecting such forgeries is crucial in various applications, including digital forensics, and image authentication. We discuss the different forgery detection methods, including block-based, keypoint-based, machine learning-based approaches, and various deep learning-based techniques, and a summary of benchmark datasets and evaluation measures is presented. The survey reveals that deep learning-based methods have shown promising results in detecting image forgeries, and the development of robust and efficient detection methods remains an active area of research. The study concludes with a discussion of future directions in image forgery detection.