Advanced Search

Show simple item record

dc.contributor.authorAydos, Fahri
dc.contributor.authorÖzbayoğlu, A. Murat
dc.contributor.authorŞirin, Yahya
dc.contributor.authorDemirci, M. Fatih
dc.date.accessioned2023-03-27T11:55:51Z
dc.date.available2023-03-27T11:55:51Z
dc.date.issued2020en_US
dc.identifier.citationAydos, F., Özbayoğlu, A. M., Şirin, Y., & Demirci, M. F. (2020). Web page classification with Google Image Search results (Version 2). arXiv. https://doi.org/10.48550/ARXIV.2006.00226en_US
dc.identifier.urihttps://doi.org/10.48550/ARXIV.2006.00226
dc.identifier.urihttps://hdl.handle.net/20.500.12436/4575
dc.description.abstractIn this paper, we introduce a novel method that combines multiple neural network results to decide the class of the input. This is the first study which used the method for web pages classification. In our model, each element is represented by multiple descriptive images. After the training process of the neural network model, each element is classified by calculating its descriptive image results. We apply our idea to the web page classification problem using Google Image Search results as descriptive images. We obtained a classification rate of 94.90% on the WebScreenshots dataset that contains 20000 web sites in 4 classes. The method is easily applicable to similar problemsen_US
dc.language.isoengen_US
dc.publisherarXiven_US
dc.identifier.doi10.48550/ARXIV.2006.0022en_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subjectWeb page classificationen_US
dc.subjectDescriptive imagesen_US
dc.subjectGoogle Image Searchen_US
dc.subjectDeep learningen_US
dc.subjectWebScreenshotsen_US
dc.titleWeb page classification with Google Image Search resultsen_US
dc.typearticleen_US
dc.departmentMühendislik ve Doğa Bilimleri Fakültesien_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.contributor.department-temp
dc.institutionauthorŞirin, Yahya


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record