Visual quality assessment of E-commerce product images using convolutional neural networks

Basit Öğe Kaydı
dc.authorid0009-0003-0309-4997
dc.authorid0000-0002-5561-4283
dc.contributor.authorTbaileh, Imad
dc.contributor.authorBağrıyanık, Selami
dc.date.accessioned2025-11-04T16:05:21Z
dc.date.available2025-11-04T16:05:21Z
dc.date.issued2025
dc.departmentFakülteler, Mühendislik ve Doğa Bilimleri Fakültesi, Bilgisayar Mühendisliği Bölümü
dc.description.abstractHigh-quality product images are vital in shaping consumer trust and driving engagement on e-commerce platforms. This study proposes a deep learning-based approach for evaluating the visual quality of product images, with the aim of improving the overall customer experience and presentation standards in online marketplaces. A custom-labeled dataset was developed, containing thousands of product images categorized into five quality levels. A convolutional neural net work (CNN) was trained to classify these images based on their visual quality. In addition, two well-known architectures, MobileNetV2 and EfficientNetB0, were trained under identical conditions to serve as benchmarks for performance com parison. The proposed CNN model achieved an accuracy of 94.93%, outperforming both MobileNetV2 (76.60%) and EfficientNetB0 (92.77%). It also delivered the highest performance in terms of precision, recall, and F1-score, confirming its effectiveness in this domain. The results highlight the CNN model’s suitability for real-time quality assessment of e-commerce images. Its strong performance and efficiency make it a promising candidate for integration into commercial platforms. Future work will investigate the use of transformer-based models and more diverse training data to further improve accuracy and generalizability.
dc.identifier.citationTbaileh, I., & Bağrıyanık, S. (2025). Visual quality assessment of E-commerce product images using convolutional neural networks. Multimedia Systems, 31(1), pp. 1-14. https://doi.org/10.1007/s00530-025-02009-8
dc.identifier.doi10.1007/s00530-025-02009-8
dc.identifier.endpage14
dc.identifier.issn1432-1882
dc.identifier.issn0942-4962
dc.identifier.issue1
dc.identifier.scopus2-s2.0-105018672726
dc.identifier.scopusqualityQ1
dc.identifier.startpage1
dc.identifier.urihttps://doi.org/10.1007/s00530-025-02009-8
dc.identifier.urihttps://hdl.handle.net/20.500.13055/1159
dc.identifier.volume31
dc.identifier.wosqualityQ2
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.indekslendigikaynakPubMed
dc.indekslendigikaynak.otherSCI-E - Science Citation Index Expanded
dc.institutionauthorBağrıyanık, Selami
dc.institutionauthorid0000-0002-5561-4283
dc.language.isoen
dc.publisherSpringer Nature Link
dc.relation.ispartofMultimedia Systems
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.subjectComputer Vision
dc.subjectNR-IQA
dc.subjectCNN
dc.subjectDeep Learning
dc.subjectImage Quality Assessment
dc.subjectE-Commerce
dc.titleVisual quality assessment of E-commerce product images using convolutional neural networks
dc.typeArticle
dspace.entity.typePublication

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Kapalı Erişim
İsim:
Tam Metin / Full Text
Boyut:
1.98 MB
Biçim:
Adobe Portable Document Format
İndir
Lisans paketi
Listeleniyor 1 - 1 / 1
Kapalı Erişim
İsim:
license.txt
Boyut:
1.17 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama:
İndir

Koleksiyon

Bilgisayar Mühendisliği Bölümü Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu