{"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/variational-multi-phase-segmentation-using","title":"Variational Multi-Phase Segmentation using High-Dimensional Local Features","arxiv_id":"1902.09863","date":"2019-02-26","proceeding":null,"authors":["Niklas Mevenkamp","Benjamin Berkels"],"abstract":"We propose a novel method for multi-phase segmentation of images based on\nhigh-dimensional local feature vectors. While the method was developed for the\nsegmentation of extremely noisy crystal images based on localized Fourier\ntransforms, the resulting framework is not tied to specific feature\ndescriptors. For instance, using local spectral histograms as features, it\nallows for robust texture segmentation. The segmentation itself is based on the\nmulti-phase Mumford-Shah model. Initializing the high-dimensional mean features\ndirectly is computationally too demanding and ill-posed in practice. This is\nresolved by projecting the features onto a low-dimensional space using\nprinciple component analysis. The resulting objective functional is minimized\nusing a convexification and the Chambolle-Pock algorithm. Numerical results are\npresented, illustrating that the algorithm is very competitive in texture\nsegmentation with state-of-the-art performance on the Prague benchmark and\nprovides new possibilities in crystal segmentation, being robust to extreme\nnoise and requiring no prior knowledge of the crystal structure.","url_abs":"http://arxiv.org/abs/1902.09863v1","url_pdf":"http://arxiv.org/pdf/1902.09863v1.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":"variational-multi-phase-segmentation-using","repo_url":"https://github.com/nmevenkamp/pcams","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"high","task_name":"Vocal Bursts Intensity Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1902.09863","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}