Rudolf Haraksim, Alexandre Anthonioz, C. Champod, M. Olsen, John Ellingsgaard, C. Busch
{"title":"Altered fingerprint detection – algorithm performance evaluation","authors":"Rudolf Haraksim, Alexandre Anthonioz, C. Champod, M. Olsen, John Ellingsgaard, C. Busch","doi":"10.1109/IWBF.2016.7449673","DOIUrl":null,"url":null,"abstract":"The purpose of this paper is to present a comparative study on the performance of altered fingerprint detection algorithms. Different algorithms from different institutions have been evaluated on two different datasets. Both datasets feature real alterations on fingers and the ground truth regarding the alteration is known a priori, as, in some cases, corresponding pre-altered fingerprints were also available. The performance obtained on both datasets produced by either reference state-of-the-art or custom-built algorithms is higher than the reported 10% EER from previous studies [1].","PeriodicalId":282164,"journal":{"name":"2016 4th International Conference on Biometrics and Forensics (IWBF)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2016-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2016 4th International Conference on Biometrics and Forensics (IWBF)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IWBF.2016.7449673","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 3
Abstract
The purpose of this paper is to present a comparative study on the performance of altered fingerprint detection algorithms. Different algorithms from different institutions have been evaluated on two different datasets. Both datasets feature real alterations on fingers and the ground truth regarding the alteration is known a priori, as, in some cases, corresponding pre-altered fingerprints were also available. The performance obtained on both datasets produced by either reference state-of-the-art or custom-built algorithms is higher than the reported 10% EER from previous studies [1].