{"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/image-forgery-localization-based-on-multi","title":"Image Forgery Localization Based on Multi-Scale Convolutional Neural Networks","arxiv_id":"1706.07842","date":"2017-06-13","proceeding":null,"authors":["Yaqi Liu","Qingxiao Guan","Xianfeng Zhao","Yun Cao"],"abstract":"In this paper, we propose to utilize Convolutional Neural Networks (CNNs) and\nthe segmentation-based multi-scale analysis to locate tampered areas in digital\nimages. First, to deal with color input sliding windows of different scales, a\nunified CNN architecture is designed. Then, we elaborately design the training\nprocedures of CNNs on sampled training patches. With a set of robust\nmulti-scale tampering detectors based on CNNs, complementary tampering\npossibility maps can be generated. Last but not least, a segmentation-based\nmethod is proposed to fuse the maps and generate the final decision map. By\nexploiting the benefits of both the small-scale and large-scale analyses, the\nsegmentation-based multi-scale analysis can lead to a performance leap in\nforgery localization of CNNs. Numerous experiments are conducted to demonstrate\nthe effectiveness and efficiency of our method.","url_abs":"http://arxiv.org/abs/1706.07842v4","url_pdf":"http://arxiv.org/pdf/1706.07842v4.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":"image-forgery-localization-based-on-multi","repo_url":"https://github.com/namtpham/image_tampering_detection_references","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"segmentation","task_name":"Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}