Development of a real-time plastic waste detection system based on deep learning to support the automation of industrial waste sorting processes

Authors

  • Latifah Listyalina Rubber and Plastic Processing Technology, Politeknik ATK Yogyakarta, Yogyakarta, Indonesia
  • Mario Sarisky Rubber and Plastic Processing Technology, Politeknik ATK Yogyakarta, Yogyakarta, Indonesia
  • Uma Fadzilia Arifin Rubber and Plastic Processing Technology, Politeknik ATK Yogyakarta, Yogyakarta, Indonesia
  • Ratna Utarianingrum Rubber and Plastic Processing Technology, Politeknik ATK Yogyakarta, Yogyakarta, Indonesia
  • Hekin Irfan Chandra Rubber and Plastic Processing Technology, Politeknik ATK Yogyakarta, Yogyakarta, Indonesia

DOI:

https://doi.org/10.31315/opsi.v18i2.15682

Keywords:

Artificial intelligence , Deep learning , Real-time detection , Plastic waste detection , Mobile application

Abstract

The accumulation of plastic waste has become one of the major environmental issues in Indonesia, where conventional waste management systems are still limited in handling and classifying various types of waste. This research aims to develop an automatic waste detection system using Artificial Intelligence (AI) and implement it in a mobile application capable of identifying plastic waste in real time. The model was trained using the WasteIn dataset, which contains annotated images of different waste categories, including plastic, paper, glass, metal, organic, and electronic waste. The YOLO11-Nano architecture was applied due to its lightweight structure and efficiency for mobile-based deployment. The trained model was then converted into TensorFlow Lite (TFLite) format and integrated into an Android Studio environment to enable real-time inference through smartphone cameras. Based on the evaluation of 36 test images, the system achieved an accuracy of 91.67%, with consistent performance in detecting plastic, paper, and organic waste. The inference time of less than 100 milliseconds per frame demonstrates the system’s feasibility for real-time mobile applications. The results indicate that the integration of deep learning and computer vision technologies can effectively support waste classification processes and contribute to sustainable waste management practices.

References

[1] R. S. Midigudla, T. Dichpally, U. Vallabhaneni, Y. Wutla, D. M. Sundaram, dan S. Jayachandran, “A comparative analysis of deep learning models for waste segregation: YOLOv8, EfficientDet, and Detectron 2,” Multimed. Tools Appl., vol. 84, no. 29, hal. 35941–35964, 2025, doi: 10.1007/s11042-025-20647-y.

[2] A. N. Matheri, Z. B. Sithole, dan B. Mohamed, “Data-Driven Circular Economy of Biowaste to Bioenergy with Conventional Prediction Modelling and Machine Learning,” Circ. Econ. Sustain., vol. 4, no. 2, hal. 929–950, 2024, doi: 10.1007/s43615-023-00329-3.

[3] R. E. V. Sesay and P. Fang, “‘Circular Economy in Municipal Solid Waste Management: Innovations and Challenges for Urban Sustainability,’” J. Environ. Prot. (Irvine,. Calif)., vol. 16, no. 2, hal. 35, 2025.

[4] W. Lu dan J. Chen, “Computer vision for solid waste sorting: A critical review of academic research,” 2022, Elsevier BV. doi: 10.1016/j.wasman.2022.02.009.

[5] S. Kunwar, “‘MWaste: A deep learning approach to manage household waste,’” Cornell Univ., vol. 2304.14498, 2023.

[6] P. S. Bhambare et al., “Artificial intelligence for sustainable environmental management in the mining sector: A review. Applied Chemical Engineering,” ACE-5756., vol. 8, no. 3, 2025.

[7] J. Gunaseelan, S. Sundaram, dan B. Mariyappan, “A Design and Implementation Using an Innovative Deep-Learning Algorithm for Garbage Segregation.,” Sensors (Basel)., vol. 23, no. 18, Sep 2023, doi: 10.3390/s23187963.

[8] Y. Chu, C. Huang, X. Xie, B. Tan, S. Kamal, dan X. Xiong, “Multilayer Hybrid Deep-Learning Method for Waste Classification and Recycling,” Comput. Intell. Neurosci., vol. 2018, hal. 1–9, Nov 2018, doi: 10.1155/2018/5060857.

[9] and L. L. Z. Feng, J. Yang, L. Chen, Z. Chen, “‘An intelligent waste-sorting and recycling device based on improved EfficientNet,’” Multidiscip. Digit. Publ. Inst., vol. 19, hal. 15987, 2022.

[10] R. Borchard, R. Zeiss, dan J. Recker, “Digitalization of waste management: Insights from German private and public waste management firms,” Waste Manag. & Res., vol. 40, no. 6, hal. 775–792, 2022, doi: 10.1177/0734242X211029173.

[11] and J. T. B. Fu, S. Li, J. Wei, Q. Li, Q. Wang, “‘A novel intelligent garbage classification system based on deep learning and an embedded linux system,’” Inst. Electr. Electron. Eng., vol. 9, hal. 131134, 2021.

[12] and N. P. L. Listyalina, R. R. Utami, U. F. Arifin, “‘The Application of Artificial Intelligence in Waste Classification as an Effort In Plastic Waste Management’.,” Telematika, vol. 21, no. 1, hal. 1–13, 2024.

[13] C. Zhihong, Z. Hebin, W. Yanbo, L. Binyan, dan L. Yu, “A vision-based robotic grasping system using deep learning for garbage sorting,” in 2017 36th Chinese Control Conference (CCC), 2017, hal. 11223–11226. doi: 10.23919/ChiCC.2017.8029147.

[14] and Y. Q. C. L.-W. Lung, Y. R. Wang, “‘Leveraging Deep Learning and Internet of Things for Dynamic Construction Site Risk Management,’” Buildings, vol. 15, no. 8, hal. 1325, 2025.

[15] and M. U. M. F. Fotovvatikhah, I. Ahmedy, R. M. Noor, “‘A Systematic Review of AI-Based Techniques for Automated Waste Classification,’” Sensors, vol. 25, no. 10, hal. 3181, 2025.

[16] N. Almtireen et al., “‘PLC-Controlled Intelligent Conveyor System with AI-Enhanced Vision for Efficient Waste Sorting,’” Appl. Sci., vol. 15, no. 3, hal. 1550, 2025.

[17] and I. B. Y. Ramadhani, L. Listyalina, “‘Design of an Arduino-Based CPM Elbow Actuator with Optocoupler Angle Sensor: Initial Study with Future Consideration for Rubber and Plastic Components,’ ,” J. Electr. Technol. UMY, vol. 9, no. 1, hal. 18, 2025.

[18] A. G. Howard et al., “‘MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications,’” arXiv Prepr., 2017.

[19] and the U. T. G. Jocher, A. Chaurasia, J. Qiu, “‘YOLO: Real-Time Object Detection,’ , 2024.,” Ultralytics, 2024.

[20] and F. W. P. Lu, S. Hsiao, J. Tang, “‘A generative-AI-based design methodology for car frontal forms design,’” Adv. Eng. Informatics, vol. 62, hal. 102835, 2024.

[21] and N. C. K. G. Mittal, K. B. Yagnik, M. Garg, “‘SpotGarbage: smartphone app to detect garbage using deep learning,’” in UbiComp ’16: Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing, 2016, hal. 940.

[22] and D. G. M. Shroff, A. Desai, “‘YOLOv8-based Waste Detection System for Recycling Plants: A Deep Learning Approach,’” in 2023 International Conference on Self Sustainable Artificial Intelligence Systems (ICSSAS), 2023, hal. 1.

[23] W. Lin, “‘YOLO-Green: A Real-Time Classification and Object Detection Model Optimized for Waste Management,’” in 2021 IEEE International Conference on Big Data (Big Data), 2021.

[24] and J. Q. Glenn Jocher, Ayush Chaurasia, “YOLOv8 vs YOLO11: Evolution of Real-Time Object Detection,” Ultralytics.

[25] and B. M. J. Gunaseelan, S. Sundaram, “‘A Design and Implementation Using an Innovative Deep-Learning Algorithm for Garbage Segregation,’” Sensors, vol. 23, no. 18, hal. 7963, 2023.

[26] and D. B. U. K. Lilhore, S. Simaiya, S. Dalal, M. Rădulescu, “‘Intelligent waste sorting for sustainable environment: A hybrid deep learning and transfer learning model,’ ,” in Gondwana Research, 2024.

[27] I. Buyung, A. Q. Munir, N. Wijaya, dan L. Listyalina, “Identifying Types of Waste as Efforts in Plastic Waste Management Based on Deep Learning,” Telematika, vol. 20, no. 3, hal. 362, 2023.

[28] and F. M. S. N. A. Rahmatulloh, I. Darmawan, A. P. Aldya, “‘WasteInNet: Deep Learning Model for Real-time Identification of Various Types of Waste,’” in Cleaner Waste Systems, 2024, hal. 100198.

[29] G. Jocher and J. Qiu, “Ultralytics YOLO11.,” https://github.com/ultralytics/ultralytics.

Downloads

Published

2025-12-30

Issue

Vol. 18 No. 2 (2025): OPSI - December 2025

Section

Article

License

Authors who publish articles in this journal agree to the following conditions:

  1. Copyright remains with the author and gives the Opsi journal the right as a priority to publish its articles with Creative Commons Attribution 4.0 International license. Which allows articles to be shared with acknowledgement of the author of the article and this journal as the place of publication.
  2. Authors can distribute their articles on a non-exclusive basis (e.g. in university repositories or books) with notification or acknowledgement of publication in Opsi journals.
  3. Authors are allowed to post their work online (e.g. on a personal website or in a university repository) before and after the submission process (see The Effect of Open Access)
 

Lisensi Creative Commons

This work is Licensed Under a Creative Commons Attribution 4.0 International license.