Plastic waste detection and classification using image recognition machine learning

Date

2025

Adviser

Lea C. Garcia

Principal

Mabel S. Buela

Abstract

Plastic pollution remains one of the most pressing environmental challenges in the Philippines, driven largely by the widespread use of single-use plastics and the lack of effective waste management systems. While existing tools like infrared-based plastic scanners are emerging globally, there remains a gap in accessible, AI-powered image recognition systems that can aid in proper waste segregation. This study aims to address that gap by developing a plastic waste scanner prototype that leverages machine learning and image recognition to identify and classify different types of plastic. Specifically, the objective was to design a system capable of recognizing various polymer types—PET, HDPE, PVC, LDPE, PP, PS, and OTHER—and providing relevant information on their recyclability, biodegradability, and potential hazards. The prototype was developed using Python and trained with YOLOv8, a state-of-the-art object detection algorithm, supported by PyTorch 2.3.1. Photographs of plastic waste samples were taken using webcams, and labeled using the labelImg tool. AI model training and testing were conducted using a high-performance desktop at the UPLB Institute of Computer Science. The model attained a mean average precision (mAP) of 82.9%, indicating a high degree of accuracy in identifying and classifying plastic types in real time. The system successfully displayed plastic classification results. Despite limitations such as a restricted data set and limited geographic scope, the study demonstrates the feasibility of integrating AI into waste segregation systems. The prototype can serve as a springboard for subsequent innovations in managing plastic waste, offering practical use for educational and waste management applications, especially in community or institutional settings. Ultimately, this research highlights the potential of machine learning as a scalable and impactful tool in the fight against plastic pollution in the Philippines.

Language

English

Location

UP Rural High School

Notes

To access this capstone, please contact the UP Rural High School Library at uprhslibrary.uplb@up.edu.ph. You may also visit the library in person, provided you secure prior confirmation from the librarian. We will be happy to assist you.

Document Type

Capstone

This document is currently not available here.

Share

COinS