Automatically Discovering Relevant Images From Web Pages

Basit Öğe Kaydı
dc.authoridUzun, Erdinç/0000-0003-4351-2244
dc.authoridOZHAN, Erkan/0000-0002-3971-2676
dc.authoridYerlikaya, Tarik/0000-0002-9888-0151
dc.authoridBulus, Halil Nusret/0000-0003-1844-6484
dc.authorwosidUzun, Erdinç/AAG-5529-2019
dc.authorwosidYerlikaya, Tarık/AGP-6489-2022
dc.authorwosidOZHAN, Erkan/N-8743-2016
dc.contributor.authorUzun, Erdinc
dc.contributor.authorOzhan, Erkan
dc.contributor.authorAgun, Hayri Volkan
dc.contributor.authorYerlikaya, Tarik
dc.contributor.authorBulus, Halil Nusret
dc.date.accessioned2024-06-12T11:17:15Z
dc.date.available2024-06-12T11:17:15Z
dc.date.issued2020
dc.departmentTrakya Üniversitesien_US
dc.description.abstractWeb pages contain irrelevant images along with relevant images. The classification of these images is an error-prone process due to the number of design variations of web pages. Using multiple web pages provides additional features that improve the performance of relevant image extraction. Traditional studies use the features extracted from a single web page. However, in this study, we enhance the performance of relevant image extraction by employing the features extracted from different web pages consisting of standard news, galleries, video pages, and link pages. The dataset obtained from these web pages contains 100 different web pages for each 200 online news websites from 58 different countries. For discovering relevant images, the most straightforward approach extracts the largest image on the web page. This approach achieves a 0.451 F-Measure score as a baseline. Then, we apply several machine learning methods using features in this dataset to find the most suitable machine learning method. The best f-Measure score is 0.822 using the AdaBoost classifier. Some of these features have been utilized in previous web data extraction studies. To the best of our knowledge, 15 new features are proposed for the first time in this study for discovering the relevant images. We compare the performance of the AdaBoost classifier on different feature sets. The proposed features improve the f-Measure by 35 percent. Besides, using only the cache feature, which is the most prominent feature, corresponds to 7 percent of this improvement.en_US
dc.identifier.doi10.1109/ACCESS.2020.3039044
dc.identifier.endpage208921en_US
dc.identifier.issn2169-3536
dc.identifier.scopus2-s2.0-85183479365en_US
dc.identifier.scopusqualityQ1en_US
dc.identifier.startpage208910en_US
dc.identifier.urihttps://doi.org/10.1109/ACCESS.2020.3039044
dc.identifier.urihttps://hdl.handle.net/20.500.14551/24630
dc.identifier.volume8en_US
dc.identifier.wosWOS:000594426400001en_US
dc.identifier.wosqualityQ2en_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherIEEE-Inst Electrical Electronics Engineers Incen_US
dc.relation.ispartofIeee Accessen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subjectWeb Pagesen_US
dc.subjectFeature Extractionen_US
dc.subjectLayouten_US
dc.subjectMachine Learningen_US
dc.subjectCrawlersen_US
dc.subjectPredictive Modelsen_US
dc.subjectTask Analysisen_US
dc.subjectImage Classificationen_US
dc.subjectImage Retrievalen_US
dc.subjectFeature Extractionen_US
dc.subjectWeb Crawlersen_US
dc.subjectWeb Miningen_US
dc.titleAutomatically Discovering Relevant Images From Web Pagesen_US
dc.typeArticleen_US

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu