Multi-label classification of line chart images using convolutional neural networks

Basit Öğe Kaydı
dc.authoridKosemen, Cem / 0000-0002-5410-9672
dc.authoridBirant, Derya / 0000-0003-3138-0432
dc.authorscopusid57195916568
dc.authorscopusid6508164583
dc.authorwosidKosemen, Cem/R-4323-2016
dc.authorwosidKosemen, Cem/AAC-8063-2021
dc.authorwosidBirant, Derya/U-6211-2017
dc.contributor.authorKösemen, Cem
dc.contributor.authorBirant, Derya
dc.date.accessioned2022-02-15T16:58:03Z
dc.date.available2022-02-15T16:58:03Z
dc.date.issued2020
dc.departmentBakırçay Üniversitesien_US
dc.description.abstractIn this paper, we propose a new convolutional neural network (CNN) architecture to build a multi-label classifier that categorizes line chart images according to their characteristics. The class labels are organized in the form of trend property (increasing or decreasing) and functional property (linear or exponential). In the proposed method, the Canny edge detection technique is applied as a data preprocessing step to increase both the classification accuracy and training speed. In addition, two different multi-label solution approaches are compared: label powerset (LP) and binary relevance (BR) methods. The experimental studies show that the proposed LP-CNN model achieves 93.75% accuracy, while the BR-CNN model reaches 92.97% accuracy on the test set, which contains real-world line chart images. The aim of this study is to build an efficient classifier that can be used for many purposes, such as automatically captioning the chart images, providing recommendations, redesigning charts, organizing a collection of chart images and developing better search engines.en_US
dc.identifier.doi10.1007/s42452-020-3055-y
dc.identifier.issn2523-3963
dc.identifier.issn2523-3971
dc.identifier.issue7en_US
dc.identifier.scopus2-s2.0-85100748090en_US
dc.identifier.scopusqualityQ2en_US
dc.identifier.urihttps://doi.org/10.1007/s42452-020-3055-y
dc.identifier.urihttps://hdl.handle.net/20.500.14034/336
dc.identifier.volume2en_US
dc.identifier.wosWOS:000543372600004en_US
dc.identifier.wosqualityN/Aen_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherSpringer International Publishing Agen_US
dc.relation.journalSn Applied Sciencesen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subjectLine chartsen_US
dc.subjectImage classificationen_US
dc.subjectMulti-label classificationen_US
dc.subjectConvolutional neural networksen_US
dc.subjectDeep learningen_US
dc.subjectMachine learningen_US
dc.subjectRecognitionen_US
dc.subjectPatternsen_US
dc.titleMulti-label classification of line chart images using convolutional neural networksen_US
dc.typeArticleen_US

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim
İsim:
Multi-label classification of line chart images using convolutional neural networks.pdf
Boyut:
2.08 MB
Biçim:
Adobe Portable Document Format
Açıklama:
Tam Metin / Full Text
İndir

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Bilgisayar Mühendisliği Bölümü Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu