{"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/accurate-and-scalable-image-clustering-based","title":"Accurate and Scalable Image Clustering Based On Sparse Representation of Camera Fingerprint","arxiv_id":"1810.07945","date":"2018-10-18","proceeding":null,"authors":["Quoc-Tin Phan","Giulia Boato","Francesco G. B. De Natale"],"abstract":"Clustering images according to their acquisition devices is a well-known\nproblem in multimedia forensics, which is typically faced by means of camera\nSensor Pattern Noise (SPN). Such an issue is challenging since SPN is a\nnoise-like signal, hard to be estimated and easy to be attenuated or destroyed\nby many factors. Moreover, the high dimensionality of SPN hinders large-scale\napplications. Existing approaches are typically based on the correlation among\nSPNs in the pixel domain, which might not be able to capture intrinsic data\nstructure in union of vector subspaces. In this paper, we propose an accurate\nclustering framework, which exploits linear dependencies among SPNs in their\nintrinsic vector subspaces. Such dependencies are encoded under sparse\nrepresentations which are obtained by solving a LASSO problem with\nnon-negativity constraint. The proposed framework is highly accurate in number\nof clusters estimation and image association. Moreover, our framework is\nscalable to the number of images and robust against double JPEG compression as\nwell as the presence of outliers, owning big potential for real-world\napplications. Experimental results on Dresden and Vision database show that our\nproposed framework can adapt well to both medium-scale and large-scale\ncontexts, and outperforms state-of-the-art methods.","url_abs":"http://arxiv.org/abs/1810.07945v2","url_pdf":"http://arxiv.org/pdf/1810.07945v2.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":"accurate-and-scalable-image-clustering-based","repo_url":"https://github.com/quoctin/residual-clustering","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"image-clustering","task_name":"Image Clustering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}