Creating an object recognition system based on computer vision in waste recycling processes
20
Anahtar Kelimeler:
computer vision- garbage recycling- CNN model - deep learning- object recognition- garbage sorting- sustainable development- data augmentationÖzet
This paper investigates the methods and results of building a computer vision-based object recognition system in waste recycling processes. The study evaluated the performance of a CNN model using a dataset of 19,762 images with 10 classes, including clothing, metal, glass, biological waste, and other recyclable materials. The model was trained for 30 epochs and stopped at the 23rd epoch using the Early Stopping mechanism, achieving a training accuracy of 95.57% and a validation accuracy of 81.68%. The results showed that the model had high training efficiency, but the low validation accuracy limited its generalization ability. The data distribution imbalance and overtraining symptoms indicated the need for additional augmentation and optimization. The study confirmed the potential of computer vision in automating waste sorting, but the model needs further development for real-time application. Future research is recommended to expand the dataset, use hybrid models, and optimize in real time. The results lay the foundation for the development of innovative solutions that contribute to environmental protection and efficient use of resources.
Referanslar
United Nations Environment Programme. (2024). Global Waste Management Outlook 2024. https://www.unep.org/resources/global-waste-management-outlook-2024
Development Aid. (2023). World Waste: Statistics by country and brief facts. https://www.developmentaid.org/news-stream/post/158158/world-waste-statistics-by-country
University of Colorado Boulder Environmental Center. (2023). The impact of recycling on climate change. https://www.colorado.edu/ecenter/2023/12/15/impact-recycling-climate-change
Earth Day Organization. (2023). How our trash impacts the environment. https://www.earthday.org/how-our-trash-impacts-the-environment/
World Bank. (2024). The world has a waste problem. Here's how to fix it. https://www.ifc.org/en/blogs/2024/the-world-has-a-waste-problem
Safe Food Advocacy Europe. (2024). Plastic Overshoot Day 2024: Global waste crisis surpasses management capacity. https://www.safefoodadvocacy.eu/plastic-overshoot-day-2024-global-waste-crisis-surpasses-management-capacity/
U.S. Environmental Protection Agency. (2024). Recycling Economic Information (REI) Report. https://www.epa.gov/smm/recycling-economic-information-rei-report
Confederation of European Paper Industries. (2024). Press release: European Paper Recycling Council Reports Strong Recycling Rates for 2024. https://www.cepi.org/press-release-european-paper-recycling-council-reports-strong-recycling-rates-for-2024/
TOMRA. (2024). Austria, Wales, Taiwan lead in recycling rates. https://www.tomra.com/news-and-media/news/2024/austria-wales-and-taiwan-leading-the-world-when-it-comes-to-rates-of-recycling
The Sustainable Agency. (2024). 50+ Recycling Facts & Stats for 2025 | Plastic, Glass & More. https://thesustainableagency.com/blog/recycling-facts-and-statistics/
Placon. (2023). Recycling Impacts on Communities. https://www.placon.com/resources/news/recycling-impacts-on-communities/
Recycleye. (2024). How Computer Vision Has Evolved and Its Role in Waste Sorting. https://recycleye.com/computer-vision-evolved-role-waste-sorting/
Forbes. (2024). Turning Trash Into Treasure: How AI Is Revolutionizing Waste Sorting. https://www.forbes.com/sites/ganeskesari/2024/05/31/turning-trash-into-treasure-how-ai-is-revolutionizing-waste-sorting/
Alliance to End Plastic Waste. (2024). How Rematics aims to make sorting recyclables smarter through AI-powered computer vision. https://www.endplasticwaste.org/what-we-do/projects/how-rematics-aims-to-make-sorting-recyclables-smarter-through-ai-powered-computer-vision
North Carolina State University. (2023). AI-Powered Waste Management System to Revolutionize Recycling. https://cnr.ncsu.edu/news/2023/11/ai-waste-management/
Zhang, Y., Wang, L., Chen, H., & Liu, Q. (2024). A Comparative Analysis of Deep Learning Models in Waste Classification. arXiv preprint arXiv:2411.02779. https://arxiv.org/pdf/2411.02779
Anonymous. (n.d.). Waste Classification and Management Using Computer Vision. Stanford University. https://cs231n.stanford.edu/papers/text_file_840523213-CS_231N_Final_Paper.pdf
Yong, H. J., Tan, K. S., & Lee, C. M. (2024). Benchmarking computer vision models for automated construction waste sorting. Resources, Conservation and Recycling. https://hub.hku.hk/bitstream/10722/353322/1/content.pdf
Shobar, M. S., Rahman, A., & Khan, M. H. (2025). Artificial Intelligence Based System for Sorting and Detection of Waste. International Journal of Artificial Intelligence and Applications, 16(5). https://thesai.org/Downloads/Volume16No5/Paper_9-Artificial_Intelligence_Based_System.pdf
Chen, X., Zhang, W., Li, Y., & Wang, J. (2025). Real-Time Household Waste Detection and Classification for Sustainable Recycling: A Deep Learning Approach. Sustainability, 17(5), 1902. https://www.mdpi.com/2071-1050/17/5/1902
Li, J., Yang, Z., & Chen, T. (2025). An automated waste classification system using deep learning techniques: Toward efficient waste recycling and environmental sustainability. Computers & Industrial Engineering. https://www.sciencedirect.com/science/article/pii/S0950705125000760
