MIT researchers latest AI(Artificial Intelligence) project aims to scan a picture of a pizza and tell you exactly how to cook it. Eventually, the research could lead up to the development of a system that could process any photo of food and produce a recipe for it — an exciting new example of AI’s potential to disrupt the food sector.
Dubbed as the PizzaGAN project, this is an experiment that wishes to teach a machine how to make a pizza simply by recognizing different aspects of cooking. This is basically done by feeding the AI various steps involved in making a pizza, such as rolling out the dough, adding the sauce, cheese, and toppings, baking it.
According to the research paper:
“Given only weak image-level supervision, the operators are trained to generate a visual layer that needs to be added to or removed from the existing image. The proposed model is able to decompose an image into an ordered sequence of layers by applying sequentially in the right order the corresponding removing modules.”
This AI project works currently only on one type of food – pizza. However, with the advances being made in the AI sector, it could be extended to other areas such as the fashion industry where digital shopping experience could be completely transformed by making it work for various layers of clothing to form an outfit, and also for other foods such as burgers and sandwiches soon.