Publication:
Multiple classifiers error rate optimization approaches of an automatic signature verification (ASV) system

Simple item page
dc.citedby0
dc.contributor.authorAhmad S.M.S.en_US
dc.contributor.authorid24721182400en_US
dc.date.accessioned2023-12-28T07:56:36Z
dc.date.available2023-12-28T07:56:36Z
dc.date.issued2007
dc.description.abstractDecision level management is a crucial aspect in an Automatic Signature Verification (ASV) system, due to its nature as the centre of decision making that decides on the validity or otherwise of an input signature sample. Here, investigations are carried out in order to improve the performance of an ASV system by applying multiple classifier approaches, where features of the system are grouped into two different subsets, namely static and dynamic sub-sets, hence having two different classifiers. In this work, three decision fusion methods, namely Majority Voting, Borda Count and cascaded multi-stage cascaded classifiers are analyzed for their effectiveness in improving the error rate performance of the ASV system. The performance analysis is based upon a database that reflects an actual user population in a real application environment, where as the system performance improvement is calculated with respect to the initial system Equal Error Rate (EER) where multiple classifiers approaches were not adopte.en_US
dc.description.natureFinalen_US
dc.identifier.epage263
dc.identifier.issueMTSV/-
dc.identifier.scopus2-s2.0-67650221672
dc.identifier.spage257
dc.identifier.urihttps://www.scopus.com/inward/record.uri?eid=2-s2.0-67650221672&partnerID=40&md5=4ea766fe0d25fb8d802c673e4e619298
dc.identifier.urihttps://irepository.uniten.edu.my/handle/123456789/29729
dc.identifier.volumeIU
dc.pagecount6
dc.sourceScopus
dc.sourcetitleVISAPP 2007 - 2nd International Conference on Computer Vision Theory and Applications, Proceedings
dc.subjectAutomatic signature verification
dc.subjectBorda count
dc.subjectEqual error rate (EER)
dc.subjectMultiple classifiers
dc.subjectComputer vision
dc.subjectDecision making
dc.subjectFace recognition
dc.subjectLearning systems
dc.subjectObject recognition
dc.subjectPattern recognition systems
dc.subjectRough set theory
dc.subjectAutomatic signature verification
dc.subjectBorda count
dc.subjectCascaded classifiers
dc.subjectDecision fusion methods
dc.subjectDecision levels
dc.subjectEqual error rate
dc.subjectEqual error rate (EER)
dc.subjectError rate
dc.subjectError rate performance
dc.subjectMajority voting
dc.subjectMulti-stage
dc.subjectMultiple classifier approach
dc.subjectMultiple classifiers
dc.subjectOptimization approach
dc.subjectPerformance analysis
dc.subjectPerformance improvements
dc.subjectReal applications
dc.subjectStatic and dynamic
dc.subjectSub-sets
dc.subjectClassifiers
dc.titleMultiple classifiers error rate optimization approaches of an automatic signature verification (ASV) systemen_US
dc.typeConference paperen_US
dspace.entity.typePublication
Files
Collections
SCOPUS