Identity Document to Selfie Face Matching Across Adolescence

Simple item page
dc.contributor.authorAlbiero, Vítor
dc.contributor.authorSrinivas, Nisha
dc.contributor.authorVillalobos Díaz, Esteban Gamaliel
dc.contributor.authorPerez Facuse, Jorge
dc.contributor.authorRosenthal, Roberto
dc.contributor.authorMery Quiroz, Domingo Arturo
dc.contributor.authorRicanek, Karl
dc.contributor.authorBowyer, Kevin W.
dc.date.accessioned2022-05-11T20:26:41Z
dc.date.available2022-05-11T20:26:41Z
dc.date.issued2020
dc.description.abstractMatching live images (“selfies†) to images from ID documents is a problem that can arise in various applications. A challenging instance of the problem arises when the face image on the ID document is from early adolescence and the live image is from later adolescence. We explore this problem using a private dataset called Chilean Young Adult (CHIYA) dataset, where we match live face images taken at age 18-19 to face images on scanned ID documents created at ages 9 to 18. State-of-the-art deep learning face matchers (e.g., ArcFace) have relatively poor accuracy for document-to-selfie face matching. To achieve higher accuracy, we fine-tune the best available open-source model with triplet loss for a few-shot learning. Experiments show that our approach achieves higher accuracy than the DocFace+ model recently developed for this problem. Our fine-tuned model was able to improve the true acceptance rate for the most difficult (largest age span) subset from 62.92% to 96.67% at a false acceptance rate of 0.01%. Our fine-tuned model is available for use by other researchers.
dc.fuente.origenIEEE
dc.identifier.doi10.1109/IJCB48548.2020.9304906
dc.identifier.eisbn978-1-7281-9186-7
dc.identifier.eissn2474-9699
dc.identifier.isbn9781728191874
dc.identifier.issn2474-9680
dc.identifier.urihttps://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=9304906
dc.identifier.urihttps://doi.org/10.1109/IJCB48548.2020.9304906
dc.identifier.urihttps://repositorio.uc.cl/handle/11534/63824
dc.identifier.wosidWOS:000723870900052
dc.information.autorucEscuela de ingeniería ; Villalobos Díaz, Esteban Gamaliel ; S/I ; 232411
dc.information.autorucEscuela de ingeniería ; Mery Quiroz, Domingo Arturo ; S/I ; 102382
dc.language.isoen
dc.nota.accesoContenido parcial
dc.publisherIEEE
dc.relation.ispartofIEEE International Joint Conference on Biometrics (IJCB) (2020 : Houston, Estados Unidos)
dc.rightsacceso restringido
dc.subjectFace recognition
dc.subjectFaces
dc.subjectTraining
dc.subjectDeep learning
dc.subjectFace detection
dc.subjectOptical character recognition software
dc.subjectOpen source software
dc.subject.ods03 Good health and well-being
dc.subject.odspa03 Salud y bienestar
dc.titleIdentity Document to Selfie Face Matching Across Adolescencees_ES
dc.typecomunicación de congreso
sipa.codpersvinculados232411
sipa.codpersvinculados102382
Files
Collections
Artículos de conferencia