Deep learning-based automated garbage image classification using light-weight models

Gozde Yolcu Öztel

doi:10.59313/jsr-a.1669471

Deep learning-based automated garbage image classification using light-weight models

Abstract

Garbage classification is essential for various aspects like health, economy and environment. The awareness of the users' separation of garbage has not been gained yet. So, garbage classification is done manually in waste sorting facilities. This is time-consuming and a difficult task; thus, automated systems are needed for this area. With this motivation, a deep learning-based system that provides automated classification of garbage has been developed in this study. In the study, five-types waste were used. These are glass, plastic, battery, paper and metal waste. MobileNetv3, ShuffleNet, EfficientNetb2, SqueezeNet, GoogleNet and MobileViT models were retrained with the transfer learning approach to classify garbage images. According to the training and testing processes performed on the Garbage Dataset, EfficientNetb2 obtained the highest performance with 0.9768 accuracy, 0.9769 precision, 0.9768 recall, and 0.9768 F1-score values. To better demonstrate the benefits of transfer learning approach, EfficientNetb2 was also trained from scratch and almost 18% smaller accuracy score than transfer learning was obtained. Moreover, to evaluate system generalization ability, the trained EficientNetb2 model was tested on another dataset. 0.9700 accuracy, 0.9706 precision, 0.9700 recall, 0.9701 f1-score values were obtained in the second dataset. The high scores on the second dataset may be related to less complex data included in this dataset and high-system generalization capacity. The future target of the study may be to integrate the system into an embedded system. Therefore, light-weight models were specially selected. These models use fewer parameters, run in less time, and require less processing load, which are requirements of the embedded systems. This system can be used in smart city projects, waste management systems, and even the development of robotic waste collection technologies. In addition to helping reduce environmental pollution, it can also contribute to reducing human labor and contributing to recycling.

Keywords

References

[1] S. Kaza, R. Y. McDonald, and L. L. Zilberti, “What a Waste 2.0: A Global Snapshot of Solid Waste Management to 2050,” The World Bank, Washington DC, 2018.
[2] C. Zhihong, Z. Hebin, W. Yanbo, L. Binyan, and L. Yu, “A vision-based robotic grasping system using deep learning for garbage sorting,” 2017 36th Chinese Control Conference (CCC), IEEE, 2017, pp. 1216–1221, doi: 10.23919/chicc.2017.8029147.
[3] X. Li, T. Li, S. Li, B. Tian, J. Ju, T. Liu, and H. Liu, “Learning fusion feature representation for garbage image classification model in human–robot interaction,” Infrared Physics & Technology, vol. 126, pp. 104457, 2023, doi: 10.1016/j.infrared.2022.104457.
[4] N. S., V. R. K. Prabu, and K. R. Bhandari, “Computer Aided Based Performance Analysis of Glioblastoma Tumor Detection Methods using UNET-CNN,” Int. J. Comput. Exp. Sci. Eng., vol. 10, no. 4, pp. 215–220, 2024, doi: 10.22399/ijcesen.515.
[5] A. Toprak, “Determination of Colorectal Cancer and Lung Cancer Related LncRNAs based on Deep Autoencoder and Deep Neural Network,” Int. J. Comput. Exp. Sci. Eng., vol. 10, no. 4, pp. 201–210, 2024, doi: 10.22399/ijcesen.636.
[6] K. B. Devananda Rao and M. Madhavi, “BCDNet: A Deep Learning Model with Improved Convolutional Neural Network for Efficient Detection of Bone Cancer Using Histology Images,” Int. J. Comput. Exp. Sci. Eng., vol. 10, no. 4, pp. 150–158, 2024, doi: 10.22399/ijcesen.430.
[7] G. E. Skar, M. Mokbel, M. N. Darwich, A. Hadi, and A. Khneisser, “Comparing deep learning and support vector machines for autonomous waste sorting,” 2016 IEEE Int. Multidisciplinary Conf. Eng. Technol. (IMCET), pp. 207–212, 2016.
[8] A. Sevinç and F. Ozyurt, “Classification of recyclable waste using deep learning architectures,” Firat University Journal of Experimental and Computational Engineering, vol. 1, no. 3, pp. 122–128, 2022, doi: 10.5505/fujece.2022.83997.

[9] N. Haque, R. Toufiq, M. D. Z. Islam, and M. A. A. T. Shoukhin, “Garbage Classification Using a Transfer Learning with Parameter Tuning,” 2024 6th Int. Conf. Electr. Eng. Inf. Commun. Technol. (ICEEICT), pp. 1252–1256, 2024, doi: 10.1109/iceeict62016.2024.10534450.
[10] E. Z. Kuang, K. R. Bhandari, and J. Gao, “Optimizing Waste Management with Advanced Object Detection for Garbage Classification,” arXiv, 2024, doi: 10.48550/ARXIV.2410.09975.
[11] Q. Zhang, Q. Yang, X. Zhang, Q. Bao, J. Su, and X. Liu, “Waste image classification based on transfer learning and convolutional neural Network,” Waste Management, vol. 135, pp. 150–157, 2021, doi: 10.1016/j.wasman.2021.08.038.
[12] Z. Kang, J. Yang, G. Li, and Z. Zhang, “An Automatic Garbage Classification System Based on Deep Learning,” IEEE Access, vol. 8, pp. 140019–140029, 2020, doi: 10.1109/access.2020.3010496.
[13] A. Khan, A. Sohail, U. Zahoora and A. S. Qureshi, "Deep Learning for Image Classification: A Comprehensive Review," in IEEE Access, vol. 8, pp. 85225-85265, 2020, doi: 10.1109/ACCESS.2020.2992555.
[14] N. Sindhwani, R. Anand, M. S., R. Shukla, M. P. Yadav ve V. Yadav, “Performance Analysis of Deep Neural Networks Using Computer Vision,” EAI Endorsed Transactions on Industrial Networks and Intelligent Systems (INIS), volume 8, issue 29, Oct 2021, doi: 10.4108/eai.13 10 2021.171318.
[15] A. Brodzicki, M. Piekarski, D. Kucharski, J. Jaworek Korjakowska ve M. Gorgoń, "Transfer Learning Methods as a New Approach in Computer Vision Tasks with Small Datasets," Foundations of Computing and Decision Sciences, cilt 45, sayı 3, ss. 179–193, Eyl 2020, doi: 10.2478/fcds 2020 0010.
[16] R. Joshi, A. Maritammanavar, A. Singh and C. Kumar, "Transfer Learning in Computer Vision: Technique and Applications," Journal of Propulsion Technology, vol. 44, no. 1, pp. 81–83, Mar. 2023, doi: 10.52783/tjjpt.v44.i1.2210.
[17] J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei, “ImageNet: A large-scale hierarchical image database,” in Proc. 2009 IEEE Conf. Comput. Vis. Pattern Recognit. Workshops (CVPR Workshops), 2009, IEEE, doi: 10.1109/cvpr.2009.5206848.
[18] I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning, MIT Press, 2016.
[19] I. Oztel, G. Yolcu, C. Oz, “Performance Comparison of Transfer Learning and Training from Scratch Approaches for Deep Facial Expression Recognition,” in Proc. 2019 28th IEEE International Conference on Computer Science and Engineering (UBMK 2019), 11-15 September 2025, Samsun, Turkey.
[20] J. Doe, & A. Smith, “Apple tree health recognition through the application of transfer learning for UAV imagery”. Journal of Precision Agriculture, 2023.
[21] L. Zhang and Y. Li, "Convolutional Neural Network for Remote-Sensing Scene Classification: Transfer Learning Analysis," Remote Sensing Letters, vol. 12, no. 3, pp. 245–258, 2021.
[22] A. W. Salehi et al., "A study of CNN and transfer learning in medical imaging: Advantages, challenges, future scope," Sustainability, vol. 15, no. 7, Art. no. 5930, 2023, doi: 10.3390/su15075930 [23] X. Cao, D. Wipf, F. Wen, G. Duan, and J. Sun, “A practical transfer learning algorithm for face verification,” in Proc. IEEE International Conference on Computer Vision (ICCV), 2013, pp. 3208–3215.
[24] A. Howard, M. Sandler, G. Chu, L.-C. Chen, B. Chen, M. Tan, W. Wang, Y. Zhu, R. Pang, V. Vasudevan, Q. V. Le, and H. Adam, “Searching for MobileNetV3 (Version 5),” arXiv, 2019. [Online]. Available: https://doi.org/10.48550/ARXIV.1905.02244.
[25] F. N. Iandola, S. Han, M. W. Moskewicz, K. Ashraf, W. J. Dally, and K. Keutzer, “SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size (Version 4),” arXiv, 2016. [Online]. Available: https://doi.org/10.48550/ARXIV.1602.07360.
[26] C. Szegedy, W. Liu, Y. Jia, P. SermaNet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich, “Going deeper with convolutions (Version 1),” arXiv, 2014. [Online]. Available: https://doi.org/10.48550/ARXIV.1409.4842.
[27] S. Mehta and M. Rastegari, “MobileViT: Light-weight, general-purpose, and mobile-friendly vision transformer (Version 2),” arXiv, 2021. [Online]. Available: https://doi.org/10.48550/ARXIV.2110.02178.
[28] M. Tan and Q. V. Le, “EfficientNetV2: Smaller models and faster training,” arXiv, 2021. [Online]. Available: https://doi.org/10.48550/ARXIV.2104.00298.
[29] X. Zhang, X. Zhou, M. Lin, and J. Sun, “ShuffleNet: An extremely efficient convolutional neural Network for mobile devices (Version 2),” arXiv, 2017. [Online]. Available: https://doi.org/10.48550/ARXIV.1707.01083.
[30] timm (PyTorch Image Models), “timm,” 2024. [Online]. Available: https://huggingface.co/timm.
[31] S. Kunwar, “Garbage dataset [Dataset],” Kaggle, 2024. [Online]. Available: https://doi.org/10.34740/KAGGLE/DSV/10182596.
[32] S. Kunwar, “Managing household waste through transfer learning (Version 1),” arXiv, 2024. [Online]. Available: https://doi.org/10.48550/ARXIV.2402.09437.
[33] Hillsborough County Recycling, “Hillsborough recycling guide,” 2023. [Online]. Available: https://www.nieonline.com/tbtimes/downloads/supplements/2023HillsboroughRecycling_ENGLISHlo.pdf.
[34] B. Huang, Z. Pan, X. Su, and L. An, “Recycling of lithium-ion batteries: Recent advances and perspectives,” J. Power Sources, vol. 399, pp. 274–286, 2018, Elsevier BV.
[35] S. Nesteruk, S. Illarionova, and A. Somov, “Image Dataset Augmentation A Survey and Taxonomy”, Measurements and Instrumentation for Machine Vision, 2024, ISBN: 9781003343783
[36] M. Mohamed, “Garbage classification (12 classes),”, Kaggle, 2020.

Details

Primary Language

English

Subjects

Computer Vision

Journal Section

Research Article

Authors

Gozde Yolcu Öztel ^*
0000-0002-7841-2131
Türkiye

Publication Date

September 30, 2025

Submission Date

April 3, 2025

Acceptance Date

September 2, 2025

Published in Issue

Year 2025 Number: 062

DOI

https://doi.org/10.59313/jsr-a.1669471

IZ

https://izlik.org/JA33TJ56CX

Cite

RIS / Bibtex

APA

Yolcu Öztel, G. (2025). Deep learning-based automated garbage image classification using light-weight models. Journal of Scientific Reports-A, 062, 171-181. https://doi.org/10.59313/jsr-a.1669471

AMA

1.Yolcu Öztel G. Deep learning-based automated garbage image classification using light-weight models. JSR-A. 2025;(062):171-181. doi:10.59313/jsr-a.1669471

Chicago

Yolcu Öztel, Gozde. 2025. “Deep Learning-Based Automated Garbage Image Classification Using Light-Weight Models”. Journal of Scientific Reports-A, nos. 062: 171-81. https://doi.org/10.59313/jsr-a.1669471.

EndNote

Yolcu Öztel G (September 1, 2025) Deep learning-based automated garbage image classification using light-weight models. Journal of Scientific Reports-A 062 171–181.

IEEE

[1]G. Yolcu Öztel, “Deep learning-based automated garbage image classification using light-weight models”, JSR-A, no. 062, pp. 171–181, Sept. 2025, doi: 10.59313/jsr-a.1669471.

ISNAD

Yolcu Öztel, Gozde. “Deep Learning-Based Automated Garbage Image Classification Using Light-Weight Models”. Journal of Scientific Reports-A. 062 (September 1, 2025): 171-181. https://doi.org/10.59313/jsr-a.1669471.

JAMA

1.Yolcu Öztel G. Deep learning-based automated garbage image classification using light-weight models. JSR-A. 2025;:171–181.

MLA

Yolcu Öztel, Gozde. “Deep Learning-Based Automated Garbage Image Classification Using Light-Weight Models”. Journal of Scientific Reports-A, no. 062, Sept. 2025, pp. 171-8, doi:10.59313/jsr-a.1669471.

Vancouver

1.Gozde Yolcu Öztel. Deep learning-based automated garbage image classification using light-weight models. JSR-A. 2025 Sep. 1;(062):171-8. doi:10.59313/jsr-a.1669471