As is the case with use case one, we can collect data through digital cameras or use an existing open source or a combination of both. We are using an existing and open source dataset for the implementation of the sorting algorithm. The dataset was collected from urban environments of the USA . As solid waste types may vary by country, it is better to update the dataset based on the country the use case will be used for. The dataset consists of six types of solid wastes: glass, paper, cardboard, plastic, metal, and trash. The dataset consists of 2,527 images, and they were annotated and organized into the following folders, as shown in the following screenshot:
United States
Great Britain
India
Germany
France
Canada
Russia
Spain
Brazil
Australia
Singapore
Hungary
Ukraine
Luxembourg
Estonia
Lithuania
South Korea
Turkey
Switzerland
Colombia
Taiwan
Chile
Norway
Ecuador
Indonesia
New Zealand
Cyprus
Denmark
Finland
Poland
Malta
Czechia
Austria
Sweden
Italy
Egypt
Belgium
Portugal
Slovenia
Ireland
Romania
Greece
Argentina
Netherlands
Bulgaria
Latvia
South Africa
Malaysia
Japan
Slovakia
Philippines
Mexico
Thailand