An Evaluation of the Layers of a Deep Network on the Optical Character Recognition Problem

Basit Öğe Kaydı
dc.contributor.authorSaygin, Rahmani
dc.contributor.authorOztimur Karadag, Ozge
dc.date.accessioned2026-01-24T12:29:00Z
dc.date.available2026-01-24T12:29:00Z
dc.date.issued2021
dc.departmentAlanya Alaaddin Keykubat Üniversitesi
dc.description29th IEEE Conference on Signal Processing and Communications Applications (SIU) -- JUN 09-11, 2021 -- ELECTR NETWORK
dc.description.abstractVarious layers of Convolutional Neural Networks, one of the most common methods of deep learning, have been examined by many researchers, and methods that will increase performance and reduce the complexity of computing have been proposed in classification using this architecture. In this paper, we investigate, over the Optical Character Recognition problem, which layers does the deep architecture owe its high performance in classification. For this purpose, we evaluated the effectiveness of the first layers of deep architecture by classifying the features extracted from deep architecture with a Support Vector Machine. Then, we evaluated the effects of these methods in classification by applying the Fully Connected Layer and Global Average Pooling Layer methods in the last layers of the deep neural network. Experiments pointed out that the deep network owes its performance to all of its layers, but alternative solutions on the upper layers of the architecture can reduce the computational complexity without a significant change in the performance..
dc.description.sponsorshipIEEE,IEEE Turkey Sect
dc.identifier.doi10.1109/SIU53274.2021.9478052
dc.identifier.isbn978-1-6654-3649-6
dc.identifier.scopus2-s2.0-85111456291
dc.identifier.scopusqualityN/A
dc.identifier.urihttps://doi.org/10.1109/SIU53274.2021.9478052
dc.identifier.urihttps://hdl.handle.net/20.500.12868/5068
dc.identifier.wosWOS:000808100700293
dc.identifier.wosqualityN/A
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.language.isotr
dc.publisherIeee
dc.relation.ispartof29th Ieee Conference on Signal Processing and Communications Applications (Siu 2021)
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.snmzKA_WoS_20260121
dc.subjectconvolutional netral network
dc.subjectglobal average pooling
dc.subjectoptical character recognition
dc.titleAn Evaluation of the Layers of a Deep Network on the Optical Character Recognition Problem
dc.title.alternativeDerin ö?renme mimarisinin katmanlarinin optik karakter tanima problemi üzerinde de?erlendirilmesi
dc.typeConference Object

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu