Clasificación de envases usando Computer Vision y Machine Learning

Abstract

The main objective of this research is to develop a functional prototype for the automated classification of glass, metal, and PET plastic containers using computer vision and machine learning. The prototype will be designed to address the problem of manual and inefficient classification in the recycling process, which contributes to the negative environmental impact caused by solid waste. To achieve this goal, a machine learning model will be trained for container detection and classification using Teachable Machine software. The model will be integrated with suitable hardware to design and build the automated container classification prototype. The validation of the prototype will be conducted through automatic container classification. Although this project is limited to the creation of a functional prototype and will not be implemented on a large scale, it is expected that the results obtained and the lessons learned can lay the groundwork for future research and developments in the field of waste management.