Authors : Bharati Badiger; Prakash O. Sarangamath; Dr. Girish Kumar D.

Volume/Issue : Volume 11 - 2026, Issue 4 - April

Google Scholar : https://tinyurl.com/2uhs4kp3

Scribd : https://tinyurl.com/au2577cm

DOI : https://doi.org/10.38124/ijisrt/26apr1990

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : Waste misclassification remains a significant challenge in modern recycling systems, leading to decreased material recovery rates and increased environmental impact. This paper presents EcoSortIQ, an intelligent recycling material identification system that applies deep learning and real-time image classification to automate the sorting of common recyclable waste. The system integrates a convolutional neural network optimized for lightweight deployment on edge devices, combined with a user-facing web interface for practical interaction. EcoSortIQ identifies materials such as plastic, metal, paper, cardboard, and glass with high accuracy under varied lighting and background conditions. Experimental evaluation demonstrates improved classification reliability compared to conventional manual sorting. EcoSortIQ provides a scalable foundation for smart recycling bins, industrial sorting facilities, and municipal waste automation systems.

Keywords : Recycling Automation, Deep Learning, Image Classification, Waste Sorting, Convolutional Neural Networks.

References :

1. S. K. Sharma and P. Singh, “AI-based waste classification using convolutional neural networks,” International Journal of Environmental Technology and Management, vol. 25, no. 3, pp. 215–230, 2022.
2. L. Andersson, T. Berg, and M. Cole, “Enhanced multimodal deep learning for automated waste detection,” IEEE Transactions on Image Processing, vol. 31, pp. 90512–90525, 2022.
3. R. Gupta, A. Verma, and N. Kumar, “Automated recycling material identification using deep learning,” IEEE Access, vol. 9, pp. 123456–123467, 2021.
4. M. Zhao and H. Li, “Image-based waste segregation with CNNs for smart cities,” Journal of Cleaner Production, vol. 278, 123456, 2021.
5. A. Patel, S. Sharma, and V. K. Jain, “Real-time waste sorting system using machine learning,” Sustainable Computing: Informatics and Systems, vol. 33, 100621, 2021.
6. J. Doe and R. Smith, “Deep learning for material recognition in recycling systems,” Procedia Computer Science, vol. 190, pp. 101–110, 2021.
7. Y. Liu et al., “Convolutional neural networks for environmental sustainability applications,” Environmental Science and Technology, vol. 55, no. 12, pp. 8234–8245, 2021.
8. D. R. Kim and P. Wong, “Vision-based intelligent waste bin systems using improved CNN architectures,” Waste Management, vol. 120, pp. 455–466, 2021.
9. H. N. Torres and L. A. Mendes, “Smart recycling stations enabled by machine learning analytics,” Sensors, vol. 21, no. 18, 6123, 2021.
10. M. Young, The Technical Writer’s Handbook, University Science, 1989.