You are here
The project aims to create a system for automatic food recognition.
Applying image processing techniques, the platform captures - at the right moment - few still images of trays with meals appearing in the field of view of a RGB camera. Subsequently, using deep learning paradigms the system has to localize and recognize each element composing the meal, in a fine-grained fashion. The actual situation with which people arrange their dishes on trays is very varied, as is the number and appearance of dishes that may be present.