The Garbage Dataset (GD): A Multi-Class Image Benchmark for Automated Waste Segregation

Suman Kunwar

doi:10.5753/jbcs.2026.7774

Authors

Suman Kunwar DWaste https://orcid.org/0000-0002-4345-1050

DOI:

https://doi.org/10.5753/jbcs.2026.7774

Keywords:

Waste Dataset, Waste Classification, Dataset Analysis, Waste Management, Computer Vision

Abstract

This study introduces the Garbage Dataset (GD), a publicly available image dataset designed to advance automated waste segregation through machine learning and computer vision. It is a diverse dataset that covers 10 categories of common household waste: Metal, Glass, Biological, Paper, Battery, Trash, Cardboard, Shoes, Clothes, and Plastic. The dataset comprises 12,259 labeled images collected through multiple methods, including the DWaste mobile app and curated web sources. The methods included rigorous validation through checksums and outlier detection, analysis of class imbalance and visual separability through PCA/t-SNE, and assessment of background complexity using entropy and saliency measures. The dataset was benchmarked using state-of-the-art deep learning models (EfficientNetV2M, EfficientNetV2S, MobileNet, ResNet50, ResNet101) evaluated on performance metrics and computational efficiency measured through energy consumption (kWh). The results of the experiment indicate that EfficientNetV2S achieved the highest performance with an accuracy of 95.13% and an F1-score of 0.95 while exhibiting a trade-off in energy consumption relative to other architectures. Analysis revealed inherent dataset characteristics including class imbalance, a skew toward high-outlier classes (Plastic, Cardboard, Paper), and brightness variations that require consideration. The main conclusion is that GD provides a valuable real-world benchmark for waste classification research while highlighting important challenges such as class imbalance, background complexity, and environmental trade-offs in model selection that must be addressed for practical deployment. The dataset is publicly released to support further research in environmental sustainability applications.

Downloads

Download data is not yet available.

References

Al-Mashhadani, I. B. (2023). Waste material classification using performance evaluation of deep learning models. Journal of Intelligent Systems, 32(1):20230064. DOI: 10.1515/jisys-2023-0064.

Arora, S., Hu, W., and Kothari, P. K. (2018). An analysis of the t-sne algorithm for data visualization. In Bubeck, S., Perchet, V., and Rigollet, P., editors, Proceedings of the 31st Conference on Learning Theory, volume 75 of Proceedings of Machine Learning Research, pages 1455-1462. PMLR. DOI: 10.48550/arxiv.1803.01768.

Bobulski, J. and Piatkowski, J. (2018). Pet waste classification method and plastic waste database - wadaba. In Choraś, M. and Choraś, R. S., editors, Image Processing and Communications Challenges 9, volume 681, pages 57-64. Springer International Publishing, Cham. DOI: 10.1007/978-3-319-68720-9_8.

Bui, T., Agarwal, S., and Collomosse, J. (2023). Trustmark: universal watermarking for arbitrary resolution images. DOI: 10.48550/arXiv.2311.18297.

Cen, A. (2020). Waste images from sushi restaurant. Available at:[link].

Courty, B., Schmidt, V., Luccioni, S., Goyal-Kamal, MarionCoutarel, Feld, B., Lecourt, J., LiamConnell, Saboni, A., Inimaz, supatomic, Léval, M., Blanche, L., Cruveiller, A., ouminasara, Zhao, F., Joshi, A., Bogroff, A., de Lavoreille, H., Laskaris, N., Abati, E., Blank, D., Wang, Z., Catovic, A., Alencon, M., Stęchły, M., Bauer, C., de Araújo, L. O. N., JPW, and MinervaBooks (2024). mlco2/codecarbon: v2.4.1. DOI: 10.5281/zenodo.11171501.

Córdova, M., Pinto, A., Hellevik, C. C., Alaliyat, S. A.-A., Hameed, I. A., Pedrini, H., and Torres, R. d. S. (2022). Litter detection with deep learning: a comparative study. Sensors, 22(2):548. DOI: 10.3390/s22020548.

Du, X., Sun, Y., Song, Y., Chi, W., Dong, L., and Zhao, X. (2025). Impact of input image resolution on deep learning performance for side-scan sonar classification: an accuracy–efficiency analysis. Remote Sensing, 17(14):2431. DOI: 10.3390/rs17142431.

Fulton, M., Hong, J., Islam, M. J., and Sattar, J. (2019). Robotic detection of marine litter using deep visual detection models. In 2019 International Conference on Robotics and Automation (ICRA), pages 5752-5758. DOI: 10.1109/ICRA.2019.8793975.

Ghosh, S., Das, N., and Nasipuri, M. (2019). Reshaping inputs for convolutional neural network: Some common and uncommon methods. Pattern Recognition, 93:79-94. DOI: 10.1016/j.patcog.2019.04.009.

Gowda, S. N. and Yuan, C. (2019). Colornet: investigating the importance of color spaces for image classification. In Jawahar, C., Li, H., Mori, G., and Schindler, K., editors, Computer Vision – ACCV 2018, volume 11364, pages 581-596. Springer International Publishing, Cham. DOI: 10.1007/978-3-030-20870-7_36.

Guo, J., Ma, J., García-Fernández, A. F., Zhang, Y., and Liang, H. (2023). A survey on image enhancement for Low-light images. Heliyon, 9(4):e14558. DOI: 10.1016/j.heliyon.2023.e14558.

Haefliger, H. (2020). Deepseawaste. Available at:[link].

He, K., Zhang, X., Ren, S., and Sun, J. (2016). Deep residual learning for image recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 770-778, Las Vegas, NV, USA. IEEE. DOI: 10.1109/CVPR.2016.90.

Hieu, N. T. and Son, N. H. (2024). The impact of input image size on the performance of deep learning models applied in cybersecurity. In 2024 RIVF International Conference on Computing and Communication Technologies (RIVF), pages 162-167, Danang, Vietnam. IEEE. DOI: 10.1109/RIVF64335.2024.11009067.

Hong, J., Fulton, M., and Sattar, J. (2020). Trashcan: a semantically-segmented dataset towards visual detection of marine debris. DOI: 10.48550/arXiv.2007.08097.

Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., and Adam, H. (2017). Mobilenets: efficient convolutional neural networks for mobile vision applications. DOI: 10.48550/arXiv.1704.04861.

Kaza, S., Shrikanth, S., and Chaudhary, S. (2021). More growth, less garbage. DOI: 10.1596/35998.

Kelly, A. (2018). Cigarette butt dataset. Available at:[link].

Kraft, M., Piechocki, M., Ptak, B., and Walas, K. (2021). Autonomous, onboard vision-based trash and litter detection in low altitude aerial images collected by an unmanned aerial vehicle. Remote Sensing, 13(5):965. DOI: 10.3390/rs13050965.

Kumsetty, N. V., Bhat Nekkare, A., S., S. K., and Kumar M., A. (2022). Trashbox: trash detection and classification using quantum transfer learning. In 2022 31st Conference of Open Innovations Association (FRUCT), pages 125-130, Helsinki, Finland. IEEE. DOI: 10.23919/FRUCT54823.2022.9770922.

Li, H. (2021). HGI-30 DATA Set. DOI: 10.5281/zenodo.4646699.

Lynch, S. (2018). Openlittermap.Com – open data on plastic pollution with blockchain rewards(Littercoin). Open Geospatial Data, Software and Standards, 3(1):6. DOI: 10.1186/s40965-018-0050-y.

Ma, D., An, Q., and Li, A. (2025). The combined effect of entropy and complexity: Human analysis of AI painting recognition ability. Systems and Soft Computing, 7:200378. DOI: 10.1016/j.sasc.2025.200378.

Mittal, G., Yagnik, K. B., Garg, M., and Krishnan, N. C. (2016). SpotGarbage: smartphone app to detect garbage using deep learning. In Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing, pages 940-945, Heidelberg Germany. ACM. DOI: 10.1145/2971648.2971731.

Mohamed, M. (2021). Garbage classification (12 classes). Available at:[link].

Nnamoko, N. (2023). Waste classification dataset. DOI: 10.17632/N3GTGM9JXJ.3.

Pal, S. (2019). Waste classification data v2. Available at:[link].

Poudel, S. and Poudyal, P. (2022). Classification of waste materials using cnn based on transfer learning. In Proceedings of the 14th Annual Meeting of the Forum for Information Retrieval Evaluation, pages 29-33, Kolkata India. ACM. DOI: 10.1145/3574318.3574345.

Proença, P. F. and Simões, P. (2020). Taco: trash annotations in context for litter detection. DOI: 10.48550/arXiv.2003.06975.

Qiu, L., Zhang, D., and Hu, Y. (2024). Research on image saliency detection based on deep neural network. IET Image Processing, 18(12):3393-3402. DOI: 10.1049/ipr2.13181.

Sekar, S. (2019). Waste Classification data. Available at:[link].

Serezhkin, A. (2020). Drinking waste classification. Available at:[link].

Shaikh, M. S., Biswal, A., Pandwal, A., Khodifad, N., and Vaghela, B. (2024). Image forgery detection using md5 & open cv. In 2024 International Conference on Emerging Research in Computational Science (ICERCS), pages 1-8. IEEE. DOI: 10.1109/ICERCS63125.2024.10895348.

Sielemann, A., Barner, V., Wolf, S., Roschani, M., Ziehn, J., and Beyerer, J. (2025). Measuring the effect of background on classification and feature importance in deep learning for av perception. In 2025 IEEE International Automated Vehicle Validation Conference (IAVVC), pages 1-8, Baden-Baden, Germany. IEEE. DOI: 10.1109/IAVVC61942.2025.11219547.

Sugiyama, D., Hidaka, M., Matsuoka, D., Murakami, K., and Kako, S. (2022). The BeachLitter dataset for image segmentation of beach litter. Data in Brief, 42:108072. DOI: 10.1016/j.dib.2022.108072.

Tan, M. and Le, Q. V. (2021). Efficientnetv2: smaller models and faster training. DOI: 10.48550/arXiv.2104.00298.

Thung, G. (2016). Trashnet dataset and classification repository. Available at:[link].

U.S. Environmental Protection Agency (2020). Advancing sustainable materials management: 2018 fact sheet. Available at:[link].

Wada, K. (2009). Checksum and cyclic redundancy check mechanism. In Liu, L. and Özsu, M. T., editors, Encyclopedia of Database Systems, pages 328-329. Springer US, Boston, MA. DOI: 10.1007/978-0-387-39940-9_1474.

Wang, T., Cai, Y., Liang, L., and Ye, D. (2020). A multi-level approach to waste object segmentation. Sensors, 20(14):3816. DOI: 10.3390/s20143816.

Wang, T.-s., Kim, G. T., Kim, M., and Jang, J. (2023). Contrast enhancement-based preprocessing process to improve deep learning object task performance and results. Applied Sciences, 13(19):10760. DOI: 10.3390/app131910760.

Wen, H., Zuo, Y., Subramanian, V., Chen, P., and Deng, J. (2025). Seeing and seeing through the glass: real and synthetic data for multi-layer depth estimation. DOI: 10.48550/arXiv.2503.11633.

Xiao, J., Guo, W., Liu, J., and Li, M. (2024). Generalization gap in data augmentation: insights from illumination. DOI: 10.48550/arXiv.2404.07514.

Yang, M. and Thung, G. (2016). Classification of trash for recyclability status. Technical Report CS229, Stanford University. Available at:[link].

Yu, J., Liu, X., Zan, F., and Peng, Y. (2025). Robust deepfake detector against deep image watermarking. PLOS One, 20(12):e0338778. DOI: 10.1371/journal.pone.0338778.

Zhou, Y., Li, X., Xiong, C., Yao, H., and Qin, C. (2025). A survey of perceptual hashing for multimedia. ACM Transactions on Multimedia Computing, Communications, and Applications, 21(7):1-28. DOI: 10.1145/3727880.