Please use this identifier to cite or link to this item: https://hdl.handle.net/20.500.11851/1961
Full metadata record
DC FieldValueLanguage
dc.contributor.authorAydoğdu, Mehmet Fatih-
dc.contributor.authorÇelik, Vakkas-
dc.contributor.authorDemirci, Muhammed Fatih-
dc.date.accessioned2019-07-10T14:42:42Z
dc.date.available2019-07-10T14:42:42Z
dc.date.issued2017
dc.identifier.citationAydogdu, M. F., Celik, V., & Demirci, M. F. (2017, January). Comparison of three different cnn architectures for age classification. In 2017 IEEE 11th International Conference on Semantic Computing (ICSC) (pp. 372-377). IEEE.en_US
dc.identifier.isbn978-1-5090-4284-5
dc.identifier.issn2325-6516
dc.identifier.urihttps://ieeexplore.ieee.org/document/7889565/-
dc.identifier.urihttps://hdl.handle.net/20.500.11851/1961-
dc.description11th IEEE International Conference on Semantic Computing (2017 : San Diego, CA)
dc.description.abstractAs one of the powerful tools of machine learning, Convolutional Neural Network (CNN) architectures are used to solve complex problems like image recognition, video analysis and natural language processing. In this paper, three different CNN architectures for age classification using face images are compared. The Morph dataset containing over 55k images is used in experiments and success of a 6-layer CNN and 2 variants of ResNet with different depths are compared. The images in the dataset are divided into 6 different age classes. While 80% of the images are used in training of the networks, the rest of the 20% is used for testing. The performance of the networks are compared according to two different criteria namely, the ability to make the estimation pointing the exact age classes of test images and the ability to make the estimation pointing the exact age classes or at most neighboring classes of the images. According to the performance results obtained, with 6-layer network, it is possible to estimate the exact or neighboring classes of the images with less than 5% error. It is shown that for a 6 class age classification problem 6-layer network is more successful than the deeper ResNet counterparts since 6-layer network is less susceptible to overfitting for this problem.en_US
dc.language.isoenen_US
dc.publisherIEEEen_US
dc.relation.ispartofIEEE International Conference on Semantic Computingen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectFace recognitionen_US
dc.subjectEstimationen_US
dc.subjectAge classificationen_US
dc.titleComparison of Three Different Cnn Architectures for Age Classificationen_US
dc.typeConference Objecten_US
dc.departmentFaculties, Faculty of Engineering, Department of Computer Engineeringen_US
dc.departmentFakülteler, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümütr_TR
dc.identifier.startpage372
dc.identifier.endpage377
dc.identifier.wosWOS:000403391300070en_US
dc.identifier.scopus2-s2.0-85018339128en_US
dc.institutionauthorDemirci, Muhammed Fatih-
dc.institutionauthorAydoğdu, Mehmet Fatih-
dc.institutionauthorÇelik, Vakkas-
dc.identifier.doi10.1109/ICSC.2017.61-
dc.authorscopusid14041575400-
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanıen_US
dc.identifier.scopusquality--
item.openairetypeConference Object-
item.languageiso639-1en-
item.grantfulltextnone-
item.fulltextNo Fulltext-
item.openairecristypehttp://purl.org/coar/resource_type/c_18cf-
item.cerifentitytypePublications-
crisitem.author.dept02.3. Department of Computer Engineering-
Appears in Collections:Bilgisayar Mühendisliği Bölümü / Department of Computer Engineering
Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection
WoS İndeksli Yayınlar Koleksiyonu / WoS Indexed Publications Collection
Show simple item record



CORE Recommender

SCOPUSTM   
Citations

9
checked on Dec 21, 2024

WEB OF SCIENCETM
Citations

15
checked on Nov 9, 2024

Page view(s)

90
checked on Dec 23, 2024

Google ScholarTM

Check




Altmetric


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