Litterati Taxonomy Guide
The LITTERATI community has developed a standardized labeling system that helps users and LITTERATI’S Machine Learning Model (LitterAI) to more accurately label images of litter.
You can download a PDF of the taxonomy guide here
How it works:
As users consistently label their litter images with OBJECT, MATERIAL & BRAND, the LitterAI is trained to better predict these specific labels in future images.
General Categories (ex. Drink, Food, Personal Hygiene) are derived from the different combinations of Objects & Materials. Where possible, a proxy weight and volume value is applied to each combination.
The combinations of Objects & Materials are then mapped to international standards such as CSIRO, OSPAR, UNEP-IOC, NOAA etc., as well as data sheets from organizations like Break Free From Plastic (BFFP).