{"title":"Successful design of biometric tests in a constrained environment","authors":"V. Dvornychenko","doi":"10.1109/AIPR.2010.5759713","DOIUrl":null,"url":null,"abstract":"The National Institute of Standards and Technology (NIST), with participation of the biometrics community, conducts evaluations of biometrics-based verification and identification systems. Of these, one of the more challenging is that of automated matching of latent fingerprints. There are many special challenges involved. First, since participation in these tests is voluntary and at the expense of the participant, NIST needs to exercise moderation in what, and how much, software is requested. As a result, it may not be possible to design tests which cover and resolve all possible outcomes. Conclusions may have to be inferred from studies that have limited results.","PeriodicalId":128378,"journal":{"name":"2010 IEEE 39th Applied Imagery Pattern Recognition Workshop (AIPR)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2010-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2010 IEEE 39th Applied Imagery Pattern Recognition Workshop (AIPR)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/AIPR.2010.5759713","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
The National Institute of Standards and Technology (NIST), with participation of the biometrics community, conducts evaluations of biometrics-based verification and identification systems. Of these, one of the more challenging is that of automated matching of latent fingerprints. There are many special challenges involved. First, since participation in these tests is voluntary and at the expense of the participant, NIST needs to exercise moderation in what, and how much, software is requested. As a result, it may not be possible to design tests which cover and resolve all possible outcomes. Conclusions may have to be inferred from studies that have limited results.