Meta-Recognition: The Theory and Practice of Recognition Score Analysis

dc.creatorScheirer, WJ
dc.creatorRocha, A
dc.creatorMicheals, RJ
dc.creatorBoult, TE
dc.date2011
dc.dateAUG
dc.date2014-07-30T14:01:31Z
dc.date2015-11-26T16:34:30Z
dc.date2014-07-30T14:01:31Z
dc.date2015-11-26T16:34:30Z
dc.date.accessioned2018-03-28T23:16:44Z
dc.date.available2018-03-28T23:16:44Z
dc.identifierIeee Transactions On Pattern Analysis And Machine Intelligence. Ieee Computer Soc, v. 33, n. 8, n. 1689, n. 1695, 2011.
dc.identifier0162-8828
dc.identifierWOS:000291807200016
dc.identifier10.1109/TPAMI.2011.54
dc.identifierhttp://www.repositorio.unicamp.br/jspui/handle/REPOSIP/56593
dc.identifierhttp://repositorio.unicamp.br/jspui/handle/REPOSIP/56593
dc.identifier.urihttp://repositorioslatinoamericanos.uchile.cl/handle/2250/1271214
dc.descriptionFundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)
dc.descriptionIn this paper, we define meta-recognition, a performance prediction method for recognition algorithms, and examine the theoretical basis for its postrecognition score analysis form through the use of the statistical extreme value theory (EVT). The ability to predict the performance of a recognition system based on its outputs for each match instance is desirable for a number of important reasons, including automatic threshold selection for determining matches and nonmatches, and automatic algorithm selection or weighting for multi-algorithm fusion. The emerging body of literature on postrecognition score analysis has been largely constrained to biometrics, where the analysis has been shown to successfully complement or replace image quality metrics as a predictor. We develop a new statistical predictor based upon the Weibull distribution, which produces accurate results on a per instance recognition basis across different recognition problems. Experimental results are provided for two different face recognition algorithms, a fingerprint recognition algorithm, a SIFT-based object recognition system, and a content-based image retrieval system.
dc.description33
dc.description8
dc.description1689
dc.description1695
dc.descriptionONR [N00014-07-M-0421, N00014-09-M-0448]
dc.descriptionUS National Science Foundation (NSF) [065025]
dc.descriptionFundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)
dc.descriptionFundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)
dc.descriptionONR [N00014-07-M-0421, N00014-09-M-0448]
dc.descriptionUS National Science Foundation (NSF) [065025]
dc.descriptionFAPESP [2010/05647-4]
dc.languageen
dc.publisherIeee Computer Soc
dc.publisherLos Alamitos
dc.publisherEUA
dc.relationIeee Transactions On Pattern Analysis And Machine Intelligence
dc.relationIEEE Trans. Pattern Anal. Mach. Intell.
dc.rightsfechado
dc.rightshttp://www.ieee.org/publications_standards/publications/rights/rights_policies.html
dc.sourceWeb of Science
dc.subjectMeta-recognition
dc.subjectperformance modeling
dc.subjectmultialgorithm fusion
dc.subjectobject recognition
dc.subjectface recognition
dc.subjectfingerprint recognition
dc.subjectcontent-based image retrieval
dc.subjectsimilarity scores
dc.subjectextreme value theory
dc.subjectPerformance
dc.titleMeta-Recognition: The Theory and Practice of Recognition Score Analysis
dc.typeArtículos de revistas


Este ítem pertenece a la siguiente institución