Enhancing CNN model classification performance through RGB angle rotation method

Basit Öğe Kaydı
dc.contributor.authorDogan, Yahya
dc.contributor.authorOzdemir, Cuneyt
dc.contributor.authorKaya, Yılmaz
dc.date.accessioned2024-12-24T19:09:56Z
dc.date.available2024-12-24T19:09:56Z
dc.date.issued2024
dc.departmentSiirt Üniversitesi
dc.description.abstractIn recent years, convolutional neural networks have significantly advanced the field of computer vision by automatically extracting features from image data. CNNs enable the modeling of complex and abstract image features using learnable filters, eliminating the need for manual feature extraction. However, combining feature maps obtained from CNNs with different approaches can lead to more complex and interpretable inferences, thereby enhancing model performance and generalizability. In this study, we propose a new method called RGB angle rotation to effectively obtain feature maps from RGB images. Our method rotates color channels at different angles and uses the angle information between channels to generate new feature maps. We then investigate the effects of integrating models trained with these feature maps into an ensemble architecture. Experimental results on the CIFAR-10 dataset show that using the proposed method in the ensemble model results in performance increases of 9.10 and 8.42% for the B and R channels, respectively, compared to the original model, while the effect of the G channel is very limited. For the CIFAR-100 dataset, the proposed method resulted in a 17.09% improvement in ensemble model performance for the R channel, a 5.06% increase for the B channel, and no significant improvement for the G channel compared to the original model. Additionally, we compared our method with traditional feature extraction methods like scale-invariant feature transform and local binary pattern and observed higher performance. In conclusion, it has been observed that the proposed RGB angle rotation method significantly impacts model performance. © The Author(s) 2024.
dc.description.sponsorshipTürkiye Bilimsel ve Teknolojik Araştırma Kurumu, TÜBİTAK
dc.identifier.doi10.1007/s00521-024-10232-z
dc.identifier.endpage20276
dc.identifier.issn0941-0643
dc.identifier.issue32
dc.identifier.scopus2-s2.0-85201273672
dc.identifier.scopusqualityQ1
dc.identifier.startpage20259
dc.identifier.urihttps://doi.org10.1007/s00521-024-10232-z
dc.identifier.urihttps://hdl.handle.net/20.500.12604/3827
dc.identifier.volume36
dc.indekslendigikaynakScopus
dc.language.isoen
dc.publisherSpringer Science and Business Media Deutschland GmbH
dc.relation.ispartofNeural Computing and Applications
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/openAccess
dc.snmzKA_20241222
dc.subjectData augmentation
dc.subjectDeep learning
dc.subjectFeature extraction
dc.subjectImage processing
dc.subjectRGB angle rotation
dc.titleEnhancing CNN model classification performance through RGB angle rotation method
dc.typeArticle

Dosyalar

Koleksiyon

Scopus İndeksli Yayınlar Koleksiyonu