On accuracy estimation and comparison of results in biometric research

Simple item page
dc.contributor.authorMery Quiroz, Domingo Arturo
dc.contributor.authorZhao, Yuning
dc.contributor.authorBowyer, Kevin
dc.date.accessioned2022-05-18T14:38:43Z
dc.date.available2022-05-18T14:38:43Z
dc.date.issued2016
dc.description.abstractThe estimated accuracy of an algorithm is the most important element of the typical biometrics research publication. Comparisons between algorithms are commonly made based on estimated accuracies reported in different publications. However, even when the same dataset is used in two publications, there is a very low frequency of the publications using the same protocol for estimating algorithm accuracy. Using the example problems of face recognition, expression recognition and gender classification, we show that the variation in estimated performance on the same dataset across different protocols can be enormous. Based on these results, we make recommendations for how to obtain performance estimates that allow reliable comparison between algorithms.
dc.fuente.origenIEEE
dc.identifier.doi10.1109/BTAS.2016.7791188
dc.identifier.isbn978-1467397339
dc.identifier.urihttps://doi.org/10.1109/BTAS.2016.7791188
dc.identifier.urihttps://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=7791188
dc.identifier.urihttps://repositorio.uc.cl/handle/11534/64152
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 Conference on Biometrics Theory, Applications and Systems (8° : 2016 : Niagara Falls, NY, Estados Unidos)
dc.rightsacceso restringido
dc.subjectProtocols
dc.subjectTraining
dc.subjectTesting
dc.subjectFace recognition
dc.subjectFace
dc.subjectDatabases
dc.subjectEstimation
dc.titleOn accuracy estimation and comparison of results in biometric researches_ES
dc.typecomunicación de congreso
sipa.codpersvinculados102382
Files
Collections
Artículos de conferencia