{"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/ted-a-tolerant-edit-distance-for-segmentation","title":"TED: A Tolerant Edit Distance for Segmentation Evaluation","arxiv_id":"1503.02291","date":"2015-03-08","proceeding":null,"authors":["Jan Funke","Francesc Moreno-Noguer","Albert Cardona","Matthew Cook"],"abstract":"In this paper, we present a novel error measure to compare a segmentation\nagainst ground truth. This measure, which we call Tolerant Edit Distance (TED),\nis motivated by two observations: (1) Some errors, like small boundary shifts,\nare tolerable in practice. Which errors are tolerable is application dependent\nand should be a parameter of the measure. (2) Non-tolerable errors have to be\ncorrected manually. The time needed to do so should be reflected by the error\nmeasure. Using integer linear programming, the TED finds the minimal weighted\nsum of split and merge errors exceeding a given tolerance criterion, and thus\nprovides a time-to-fix estimate. In contrast to commonly used measures like\nRand index or variation of information, the TED (1) does not count small, but\ntolerable, differences, (2) provides intuitive numbers, (3) gives a time-to-fix\nestimate, and (4) can localize and classify the type of errors. By supporting\nboth isotropic and anisotropic volumes and having a flexible tolerance\ncriterion, the TED can be adapted to different requirements. On example\nsegmentations for 3D neuron segmentation, we demonstrate that the TED is\ncapable of counting topological errors, while ignoring small boundary shifts.","url_abs":"http://arxiv.org/abs/1503.02291v3","url_pdf":"http://arxiv.org/pdf/1503.02291v3.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":"ted-a-tolerant-edit-distance-for-segmentation","repo_url":"https://github.com/funkey/ted","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[],"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}