You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Artificial Intelligence at Open Food Facts is there to help us accelerate our mission and the effort of our volunteers for more food transparency. Extracting data, supporting useful features, ensuring quality…these are only some of the many opportunities on a 2,7M+ annotated dataset 🤯
Meta project to extract the various variables of the Eco-Score: - packaging type and shape - origins of ingredients (inside or outside ingredient lists) - specific labels (as image or text)
Increase insight validation, either by - increasing distribution (though apps, 3rd party apps, games…) - increasing ability to validate them automatically
There are a lot of things to detect on a packaging. While we can add many individual detections (and that's very fine, there are some good and impactful examples in this project), we should aim to build general purpose systems that will scale across languages and kinds of detection (eg a system abl
Insights might be generated from newer or older images, or from images that were uploaded by error for the product. As a result they might not be true anymore, or in contradiction with one another. While manual review should prevent this, we should flesh out ways to check consistency, and build an