Please use this identifier to cite or link to this item: http://dspace.dtu.ac.in:8080/jspui/handle/repository/19215
Full metadata record
DC FieldValueLanguage
dc.contributor.authorSHAND, SHIPRA-
dc.date.accessioned2022-06-30T07:33:05Z-
dc.date.available2022-06-30T07:33:05Z-
dc.date.issued2022-05-
dc.identifier.urihttp://dspace.dtu.ac.in:8080/jspui/handle/repository/19215-
dc.description.abstractBiometric emerging and promising technology for identifying and validating a person. It is very strong, and it is accurate. Hard to copy, model, share, it distributes and cannot be stolen or forgotten. Combining more than one biometric the feature offers a promising solution to provide additional security. The traditional method of a person's identity and identity are determined through use of Biometric-Technology. The main purpose of this research project is to design and suggest an in-depth learning model: 3D convolutional neural network (3D-CNN) a category based on multiple biometric fingerprints, face recognition system and iris. To remove the feature, Densenet-201 was used. To improve functionality, feature level integration is used. Suggested Aquila Optimizer tuning separator parameter to determine the efficiency of the proposed model. Test results look at different parameters like this Equal Error Rate (EER), False Acceptance Rate (FAR), False Rejection Rate (FRR) and Accuracy showing the performance of the proposed model better there are other development models, which prove that the required identity is real or fake.en_US
dc.language.isoenen_US
dc.relation.ispartofseriesTD-5781;-
dc.subject3D-CNNen_US
dc.subjectAQUILA OPTIMIZATION ALGORITHMen_US
dc.subjectMULTI BIOMETRIC SYSTEMen_US
dc.subjectDENSENET 201en_US
dc.titleA MULTI BIOMETRIC SYSTEM BASED ON HYBRID DENSENET 201-3D CNN CLASSIFIES AND AQUILA OPTIMIZATION ALGORITHM FOR FINGERPRINT-IRIS-FACEen_US
dc.typeThesisen_US
Appears in Collections:M.E./M.Tech. Computer Engineering

Files in This Item:
File Description SizeFormat 
Shipra Shand M.TEch..pdf1.62 MBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.