Food Recognition for Smart Restaurants and Self-Service Cafes

In recent years, deep learning has been applied to different tasks in the food recognition field. Some promising solutions have been proposed. Due to the complexity of background food, the problem of pattern recognition on a limited dataset is still challenging. Experiments were conducted on a self-collected dataset with canteen trays, containing images of various dishes depending on the day of the week. The main objective of this work is to compare the effectiveness of modern object detection architectures, namely, YOLO_v5, YOLO_v6, YOLO_v7, and YOLO_v5, with a custom classifier. The experimental results showed that the custom classifier was needed to effectively distinguish dishes with high performance.