Recyclable Waste Image Dataset

This dataset contains a representative subset of the original dataset developed during the Master's dissertation entitled "Uso da Inteligência Artificial nos Processos de Pré-Reciclagem" at the Instituto Superior de Engenharia do Porto (ISEP). Only the images collected by the author are included in this public release.

The complete dataset consisted of 8068 images distributed across five recyclable waste categories: paper, cardboard, plastic, metal and glass. The dataset combined images collected by the author in real-world environments with images obtained from publicly available datasets. Due to licensing restrictions associated with third-party datasets, only a subset of the author-collected images is included in this public release.This subset contains 1,000 images acquired by the author in municipal waste management facilities, urban public spaces and domestic environments.

The dataset is intended to support future research in computer vision, object detection and automated waste sorting systems.