{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/noiseprint-a-cnn-based-camera-model","title":"Noiseprint: a CNN-based camera model fingerprint","arxiv_id":"1808.08396","date":"2018-08-25","proceeding":null,"authors":["Davide Cozzolino","Luisa Verdoliva"],"abstract":"Forensic analyses of digital images rely heavily on the traces of in-camera\nand out-camera processes left on the acquired images. Such traces represent a\nsort of camera fingerprint. If one is able to recover them, by suppressing the\nhigh-level scene content and other disturbances, a number of forensic tasks can\nbe easily accomplished. A notable example is the PRNU pattern, which can be\nregarded as a device fingerprint, and has received great attention in\nmultimedia forensics. In this paper we propose a method to extract a camera\nmodel fingerprint, called noiseprint, where the scene content is largely\nsuppressed and model-related artifacts are enhanced. This is obtained by means\nof a Siamese network, which is trained with pairs of image patches coming from\nthe same (label +1) or different (label -1) cameras. Although noiseprints can\nbe used for a large variety of forensic tasks, here we focus on image forgery\nlocalization. Experiments on several datasets widespread in the forensic\ncommunity show noiseprint-based methods to provide state-of-the-art\nperformance.","url_abs":"http://arxiv.org/abs/1808.08396v1","url_pdf":"http://arxiv.org/pdf/1808.08396v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"noiseprint-a-cnn-based-camera-model","repo_url":"https://github.com/grip-unina/noiseprint","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"noiseprint-a-cnn-based-camera-model","repo_url":"https://github.com/RonyAbecidan/noiseprint-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"model","task_name":"model"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1808.08396","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}