{"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/iris-presentation-attack-detection-based-on","title":"Iris Presentation Attack Detection Based on Photometric Stereo Features","arxiv_id":"1811.07252","date":"2018-11-18","proceeding":null,"authors":["Adam Czajka","Zhaoyuan Fang","Kevin W. Bowyer"],"abstract":"We propose a new iris presentation attack detection method using\nthree-dimensional features of an observed iris region estimated by photometric\nstereo. Our implementation uses a pair of iris images acquired by a common\ncommercial iris sensor (LG 4000). No hardware modifications of any kind are\nrequired. Our approach should be applicable to any iris sensor that can\nilluminate the eye from two different directions. Each iris image in the pair\nis captured under near-infrared illumination at a different angle relative to\nthe eye. Photometric stereo is used to estimate surface normal vectors in the\nnon-occluded portions of the iris region. The variability of the normal vectors\nis used as the presentation attack detection score. This score is larger for a\ntexture that is irregularly opaque and printed on a convex contact lens, and is\nsmaller for an authentic iris texture. Thus the problem is formulated as binary\nclassification into (a) an eye wearing textured contact lens and (b) the\ntexture of an actual iris surface (possibly seen through a clear contact lens).\nExperiments were carried out on a database of approx. 2,900 iris image pairs\nacquired from approx. 100 subjects. Our method was able to correctly classify\nover 95% of samples when tested on contact lens brands unseen in training, and\nover 98% of samples when the contact lens brand was seen during training. The\nsource codes of the method are made available to other researchers.","url_abs":"http://arxiv.org/abs/1811.07252v1","url_pdf":"http://arxiv.org/pdf/1811.07252v1.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":"iris-presentation-attack-detection-based-on","repo_url":"https://github.com/CVRL/PhotometricStereoIrisPAD","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"iris-presentation-attack-detection-based-on","repo_url":"https://github.com/CVRL/RaspberryPiOpenSourceIris","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"binary-classification","task_name":"Binary Classification"},{"task_slug":"cross-domain-iris-presentation-attack","task_name":"Cross-Domain Iris Presentation Attack Detection"}],"methods":[],"datasets_introduced":[{"slug":"ndpsid-wacv-2019","name":"NDPSID - WACV 2019","full_name":"Notre Dame Photometric Stereo Iris Dataset"}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}