{"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/pure-robust-pupil-detection-for-real-time","title":"PuRe: Robust pupil detection for real-time pervasive eye tracking","arxiv_id":"1712.08900","date":"2017-12-24","proceeding":null,"authors":["Thiago Santini","Wolfgang Fuhl","Enkelejda Kasneci"],"abstract":"Real-time, accurate, and robust pupil detection is an essential prerequisite\nto enable pervasive eye-tracking and its applications -- e.g., gaze-based human\ncomputer interaction, health monitoring, foveated rendering, and advanced\ndriver assistance. However, automated pupil detection has proved to be an\nintricate task in real-world scenarios due to a large mixture of challenges\nsuch as quickly changing illumination and occlusions. In this paper, we\nintroduce the Pupil Reconstructor PuRe, a method for pupil detection in\npervasive scenarios based on a novel edge segment selection and conditional\nsegment combination schemes; the method also includes a confidence measure for\nthe detected pupil. The proposed method was evaluated on over 316,000 images\nacquired with four distinct head-mounted eye tracking devices. Results show a\npupil detection rate improvement of over 10 percentage points w.r.t.\nstate-of-the-art algorithms in the two most challenging data sets (6.46 for all\ndata sets), further pushing the envelope for pupil detection. Moreover, we\nadvance the evaluation protocol of pupil detection algorithms by also\nconsidering eye images in which pupils are not present. In this aspect, PuRe\nimproved precision and specificity w.r.t. state-of-the-art algorithms by 25.05\nand 10.94 percentage points, respectively, demonstrating the meaningfulness of\nPuRe's confidence measure. PuRe operates in real-time for modern eye trackers\n(at 120 fps).","url_abs":"http://arxiv.org/abs/1712.08900v1","url_pdf":"http://arxiv.org/pdf/1712.08900v1.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":"pure-robust-pupil-detection-for-real-time","repo_url":"https://github.com/ARandomOWL/window-gaze","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"pupil-detection","task_name":"Pupil Detection"},{"task_slug":"specificity","task_name":"Specificity"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}