Waste Classification Dataset

Cite as:
Nnamoko, N., Barrowclough, J. and Procter, J. (2022) ‘Solid Waste Image Classification Using Deep Convolutional Neural Network’, Infrastructures, 7(4), p. 47. doi:10.3390/infrastructures7040047
----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------

Data Description
The dataset provides a collection of 24,705 images of solid household waste, categorised into two classes: organic (13,880) and recyclable (10,825) . The data is a restructured and represented version of the original dataset by Sashaank Sekar available at https://www.kaggle.com/techsash/waste-classification-data. The original dataset from Kaggle consists of 25,077 images of organic (13,966) and recyclable (11,111) images. However, performed som clean-up operations explained in the "further note" to reduce the data to 24,705 with (13,880 organic) and (10,825 recyclable) The restructured data has been used in a research study undertaken by academics and researchers at Computer Science Department, Edge Hill University, United Kingdom.

To encourage reproducibility of the experiments and results reported, the modified data; a Jupyter notebook (.ipynb) file useful to apply data augmentation on the dataset; and a Jupyter notebook (.ipynb) file useful to replicate the experiments has been provided.