{"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/domain-specific-human-inspired-binarized","title":"Domain-Specific Human-Inspired Binarized Statistical Image Features for Iris Recognition","arxiv_id":"1807.05248","date":"2018-07-13","proceeding":null,"authors":["Adam Czajka","Daniel Moreira","Kevin W. Bowyer","Patrick J. Flynn"],"abstract":"Binarized statistical image features (BSIF) have been successfully used for\ntexture analysis in many computer vision tasks, including iris recognition and\nbiometric presentation attack detection. One important point is that all\napplications of BSIF in iris recognition have used the original BSIF filters,\nwhich were trained on image patches extracted from natural images. This paper\ntests the question of whether domain-specific BSIF can give better performance\nthan the default BSIF. The second important point is in the selection of image\npatches to use in training for BSIF. Can image patches derived from\neye-tracking experiments, in which humans perform an iris recognition task,\ngive better performance than random patches? Our results say that (1)\ndomain-specific BSIF features can out-perform the default BSIF features, and\n(2) selecting image patches in a task-specific manner guided by human\nperformance can out-perform selecting random patches. These results are\nimportant because BSIF is often regarded as a generic texture tool that does\nnot need any domain adaptation, and human-task-guided selection of patches for\ntraining has never (to our knowledge) been done. This paper follows the\nreproducible research requirements, and the new iris-domain-specific BSIF\nfilters, the patches used in filter training, the database used in testing and\nthe source codes of the designed iris recognition method are made available\nalong with this paper to facilitate applications of this concept.","url_abs":"http://arxiv.org/abs/1807.05248v2","url_pdf":"http://arxiv.org/pdf/1807.05248v2.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":"domain-specific-human-inspired-binarized","repo_url":"https://github.com/CVRL/domain-specific-BSIF-for-iris-recognition","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"domain-specific-human-inspired-binarized","repo_url":"https://github.com/aczajka/iris-recognition---pm-diseased-human-driven-bsif","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"iris-recognition","task_name":"Iris Recognition"},{"task_slug":"texture-classification","task_name":"Texture Classification"}],"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}