Abstract—This research establishes a Digital Image Processing (DIP)-assisted approach for the identification and classification of primary garbage kinds conveyed by rivers. Various classification models were employed to rectify accuracy deficiencies, and the most proficient model, determined through performance evaluations, was chosen as the basis for an automated trash categorization system. Monitoring stations in Suratthani and Songkhla, prominent metropolitan centers in southern Thailand, were utilized to evaluate the overall quantity of plastic garbage released into the ocean. Classification tasks were performed with Gaussian Support Vector Machine (G-SVM) and Quadratic Support Vector Machine (Q-SVM) models.
The findings reveal that the Suratthani River released 1,350 plastic trash items, 720 leaf litter pieces, 130 foam fragments, 233 recognized lipid sheets, and 282 unidentified materials throughout a one-month period during system deployment. In Songkhla Province, 116 plastic fragments and 780 lipid sheets were discovered affixed to unidentified substances. The system is capable of distinguishing lipid sheets, which is a limitation of other classification systems. Additionally, it determines that river waste management should prioritize this type of leakage, as it has the potential to cause the accumulation of small plastics in the river system. These findings highlight the significance of modern digital image processing and machine learning techniques in the surveillance and management of plastic pollution in aquatic environments.
Keywords—ocean, plastic waste, digital image processing, SVM, waste management
Cite: Somprasong Komsoon, Assawadithalerd Mongkholchai, and Manorot Panason, "Development and Application of an Automatic River-Waste Classification System in Surat Thani and Songkhla, Thailand," International Journal of Environmental Science and Development vol. 16, no. 4, pp. 234-242, 2025.
Copyright © 2025 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).