{"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/pixel-level-alignment-of-facial-images-for","title":"Pixel-Level Alignment of Facial Images for High Accuracy Recognition Using Ensemble of Patches","arxiv_id":"1802.02438","date":"2018-02-07","proceeding":null,"authors":["Hoda Mohammadzade","Amirhossein Sayyafan","Benyamin Ghojogh"],"abstract":"The variation of pose, illumination and expression makes face recognition\nstill a challenging problem. As a pre-processing in holistic approaches, faces\nare usually aligned by eyes. The proposed method tries to perform a pixel\nalignment rather than eye-alignment by mapping the geometry of faces to a\nreference face while keeping their own textures. The proposed geometry\nalignment not only creates a meaningful correspondence among every pixel of all\nfaces, but also removes expression and pose variations effectively. The\ngeometry alignment is performed pixel-wise, i.e., every pixel of the face is\ncorresponded to a pixel of the reference face. In the proposed method, the\ninformation of intensity and geometry of faces are separated properly, trained\nby separate classifiers, and finally fused together to recognize human faces.\nExperimental results show a great improvement using the proposed method in\ncomparison to eye-aligned recognition. For instance, at the false acceptance\nrate of 0.001, the recognition rates are respectively improved by 24% and 33%\nin Yale and AT&T datasets. In LFW dataset, which is a challenging big dataset,\nimprovement is 20% at FAR of 0.1.","url_abs":"http://arxiv.org/abs/1802.02438v1","url_pdf":"http://arxiv.org/pdf/1802.02438v1.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":"pixel-level-alignment-of-facial-images-for","repo_url":"https://github.com/bghojogh/Pixel-Aligned-Face-Recognition","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"face-alignment","task_name":"Face Alignment"},{"task_slug":"face-recognition","task_name":"Face Recognition"},{"task_slug":"face-reconstruction","task_name":"Face Reconstruction"},{"task_slug":"face-to-face-translation","task_name":"Face to Face Translation"}],"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}