 Good morning everyone and thank you all for being here. It's great to talk at FOSDEMM. So I'm going to talk to present to you today OpenFoodFact, which is a bit like Wikipedia of food. So OpenFoodFact is all about this problem that many of us have in the supermarket about choosing which pack should I pick for my children. So should I flip over each and every pack and read the nutrition table? Personally, I've never managed to understand it. It's a lot of figures, so you have to do that for each and every single pack if you want to make an informed choice on food. Also, as you might have heard, the impact of food on public health is massive. It's the third cause of unwell issues with humans. It has many preventable causes, many levers that you can pull to improve the situation. And we wondered if citizens have managed to create with Wikipedia the best encyclopedia in the world. If citizens have managed to create the most accurate map in the world, why can't we do it with food products? And that's what OpenFoodFact is set out to do. So we have gathered 1.1 million products from all over the world. So that's the website of OpenFoodFact. And the intent is to decipher labels which you can also do with the OpenFoodFact app. The mechanism is simple. You just take a product, you look for the barcode and you scan it with the app. And you will get valuable information such as the Nutriscore about nutritional quality, the NOVA group which informs you about the level of transformation of the product. And finally in France, the carbon impact. Which tells you if the product is not only good for you, but also good for the planet. And it's collaborative, much like Wikipedia. If the product is not there yet, you just take free photos, front, ingredients and nutrition and in a minute you can get those scores for any product in the world. We also decipher those e-numbers that you can see on the products, those additives. We're using FSA data scientific evaluations. So you get, depending on your age, the level of over exposure for each and every single additive. You can also compare products. When you are in a store and you don't know which seal package you want to pick, you can basically weave the app, compare many products side to side and make the better choice based on the rational factors. You can do that of course. This is the photo that you saw earlier. This photo has data. So you can basically look at all the breakfast cereals and pick the right one. This is the one I haven't been eating and this was the one I've been eating as a child, smacks. You have to imagine that half of the size is pure sugar, 43% of it. Of course, it's data of public interest, so it has to be open. So our data is under the open database license, which requires you to be free for all and all use to attribute and finally to share alike. And we've managed to have quite a lot of impact. We are a French project, but we know the community is international. Mostly European. So we have one million products that have been contributed by volunteers like you, me and producers alike. We have 182 countries where we have products. If you're going to North Korea, we still have no North Korean products in the database. We have 1.5 million so far users benefiting from the NutriScore and the Nova. And as it's open, as we have an open API and open data export, there are more than 200 apps and services using the data to do various things. What's more interesting even to us is the scientific paper that use open food fact to make science progress. So whether they want to study additives or the impact of transformation of food, that's possible using open data. And finally, we have 25,000 people who have registered. I mean, we don't ask for your personal data, registration is optional, but 25,000 people who have decided to sign up and to be an active part of food transparency. And we can do many, many things with open data. For instance, this is Fanta in Italy. It has 12-person fruit. This is Fanta in Serbia. It has three-person fruit. This is Fanta in Portugal. It has eight-person fruit plus sugar or eight high fructose corn syrup. And in the Réunion, which is a French island, it has zero-person fruit. So that's the kind of thing you can do when you have open data about your food. That's another thing. In terms of impact, you may have heard, if you're about the NutriScore, that's a picture, one, sorry, my clicker is not responding, that's a picture that one of our contributors did using an image editor, and he put the NutriScore on each, every single product. Fast forward a couple of years later, that's what we are seeing in French stores. It's not only, it's not just applications anymore, it's the real world. So you can see NutriScore that is still not compulsory in France, but producers think, no, it's good marketing to display it on their product. So this shows the kind of impact like open data and apps can have. Our source are still citizen crowdsourcing, of course. So using the app, you can basically create data, the third-party apps that also bring data. But no producers are taking note and providing data as well. So you might recognize some of those brands. Many of them are French, but they are beginning to have some international ones. And we want to help manufacturers make healthy the better, the default choice. Just like a computer, we want the default choice to be healthier. And that's why we're providing, thanks to the French prevention organism, the national French Santé public organism, we are making a platform for them to find opportunities to improve their products. So for instance, if they have a beef preparation, they can find opportunities to improve the NutriScore or to reduce fat. Things that are possible to do for them without altering too much the taste and that can benefit everyone, even people who are not using OpenFoodFact. And we're trying to extend the impact beyond food. We have started to do cosmetics with OpenDutyFact. So same principle, you scan a barcode. You have those latent ingredients. I don't know if you've tried reading your bottle of shampoo, but you can't basically understand what's on it. So we try to decipher all that to detect 17 problematic substances and show them to you in the OpenFoodFact app. So great, that's very cool. How can I contribute? The thing is, as you've seen, you can have impact for all. People who are blind, for instance, can't see the labels. So being able to read the labels without having in full autonomy is important. That's the kind of impact you can have by contributing to OpenFoodFact. And we're not focused on France or Belgium. We want to have this impact on the whole world. So basically, this is a photo in Vietnam. You see they have a large grocery ale, but ultra processed food is gaining a field even with this fresh food culture. So you can have an impact on many people and in many countries. And we have many exciting projects that you can contribute to. So we have the native apps for Android and iOS. So if you're an Android or iOS developer, you can help with that. We have the new cross-platform Flutter app that will be easier to use for an even broader impact that we're starting planning. We have the OpenFoodFact artificial intelligence called Robotof, which is able to read labels. So if you're a Python or a TensorFlow addict, you can help with that. We have the OpenFoodFact database and backend. So if you code in Perl, JavaScript, Python, you're very welcome as well. And then on top of that, gamification projects in JavaScript and design and front-end if you're more of a CSS person. So this is very quickly some kind of stuff that we do using artificial intelligence. For instance, we detect the nature score. And also, if you live in a country, in any country, actually, you can help. And even if you don't have any particular technical skills, you can help improve the support for your countries. There are so many food labels, so many food categories that we need to help translating them into your language and expanding the knowledge of OpenFoodFact. Similarly, you can help improving gradient detection in your country so that we can compute the NOVA and detect additives. And you can help with our growing environmental effort to basically understand better if the food has an impact on the planet. So this is, for instance, a map of all the European food factories that we made thanks to the data. So many ways to contribute, scanning new products and adding them to OpenFoodFact. Translating OpenFoodFact into your language, there's a lot to translate. Spreading the word in your countries, among your friends in the media, designing, making the interfaces better. We have much room for progress there. Hacking, of course. And fixing bugs that are in OpenFoodFact. And with this voluntary effort, we've been able to achieve many great things in the past year. For instance, we have a brand new API documentation. Thanks also to Google's Season of Dog program. So it's easier to basically manipulate the data and play with food. I also would like to thank NLNet for its support. We are going to build a privacy-first recommendation engine that will let you make better choices based on your preference and the data won't leave your cell phone. So basically, you will be able to find the best azon nuts spread. I mean, Nutella is obviously E, you will be able to find better solutions on your device based tailor-made to your, if you're a vegan, if you have allergies, that will be able to take that into account. So thank you NLNet. And finally, we are part of this year of Google, we are a candidate to Google Summer of Code. So if you want to get involved, either as a student or as a mentor, you're very welcome to do so. And as you've seen, many exciting projects to work on. So let's keep in touch. Either on the website, contact, we also have a chat room. And you can also donate because OpenFoodFact is a non-profit. It's a volunteer organization. And finally to conclude, come play with food. Thank you. Thanks for the talk first. I tried the app from Asteroid the other day and I was surprised that it's only with scanning, so no textual input, is that right? But can you... That all the things I could to contribute is with scanning images, so taking pictures instead of entering something menu-like, for example, with OpenStreetMed, is that correct? So you can actually, the first thing that the app will ask you is take picture because that's the source of the data. And if you don't have time, others can finish the work for you. But if you click on the edit button, you can enter structure data very much like OpenStreetMed, for instance. That's a very good question and I'm glad you asked. We're not scientists, so we... Oh, sorry. So the question is how do we grade, for instance, NutriScore, NOVA, how do we grade products? So we are not scientists, first point. So we rely on scientific work. So NutriScore is an open formula by Professor Serge Jacques Berg on nutritional... So it takes into account fat, salt, sugar. And for the NOVA, it's a scientific work by Professor Montero. So the data is open. We ask the methodology to be open as well. If any of you have more questions, I'll be just next door.