EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Comparing Robust Image Retrieval and Waste Classification Using Deep Learning and Geometric Transformations

Jakkrit Onshaunjit, Wichian Ooppakaew, Anuruk Prommakhot, Jakkree Srinonchat

Electronics · 14.07.2026 · 15 (14) · 3098

DOI: 10.3390/electronics15143098 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 14.07.2026. Verfasst von Jakkrit Onshaunjit und 3 weiteren Autor:innen. Die Arbeit nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science, Research and Innovation Fund, Thailand Science Research and Innovation, Rajamangala University of Technology Thanyaburi.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Smart waste classification and image retrieval are important for recycling, resource recovery, and circular-economy applications. This study presents a comparative deep learning framework for waste classification and content-based image retrieval (CBIR) under geometric transformations. Rather than proposing a single fused architecture, the study systematically investigates three key design factors: backbone architecture, classifier-head design, and loss-function selection. A custom waste image dataset comprising 1000 images across 10 waste categories was used throughout the experiments. The evaluated backbone architectures included ResNet18, ResNet34, and ResNet50, while the classifier heads consisted of a fully connected classifier, a DenseNet201-based classifier, and a VGG16-based classifier. In addition, three loss functions—cross-entropy, label smoothing, and ArcFace—were evaluated under identical experimental conditions. The results show that ResNet50 combined with a DenseNet201-based classifier and ArcFace achieved the highest classification performance, reaching a 98.4% accuracy and 98.3% F1-score. ArcFace also improved feature discriminability and enhanced retrieval effectiveness, with the best configuration achieving a 98.1% mean average precision (mAP). Robustness evaluation under rotation and scaling transformations demonstrated that the proposed framework maintained stable performance under geometric variations. Although ResNet50 achieved the highest accuracy, ResNet34 combined with a fully connected classifier and ArcFace provided a favorable balance between recognition performance and model complexity. These findings demonstrate that backbone depth, classifier-head design, and loss-function selection all play important roles in determining waste classification and retrieval performance.

Förderung

  • National Science, Research and Innovation Fund, Thailand Science Research and Innovation
  • Rajamangala University of Technology Thanyaburi

Zitieren

APA

Onshaunjit, J., Ooppakaew, W., Prommakhot, A., & Srinonchat, J. (2026). Comparing Robust Image Retrieval and Waste Classification Using Deep Learning and Geometric Transformations. Electronics, 15(14), 3098. https://doi.org/10.3390/electronics15143098

Vancouver

Onshaunjit J, Ooppakaew W, Prommakhot A, Srinonchat J. Comparing Robust Image Retrieval and Waste Classification Using Deep Learning and Geometric Transformations. Electronics. 2026;15(14):3098. doi:10.3390/electronics15143098

BibTeX
@article{Onshaunjit2026,
  author = {Onshaunjit, Jakkrit and Ooppakaew, Wichian and Prommakhot, Anuruk and Srinonchat, Jakkree},
  title = {Comparing Robust Image Retrieval and Waste Classification Using Deep Learning and Geometric Transformations},
  journal = {Electronics},
  year = {2026},
  volume = {15},
  number = {14},
  pages = {3098},
  doi = {10.3390/electronics15143098}
}
Kostenlos starten →