Sushi Dish - Object detection and classification from real images

TL;DR

This paper presents an automated system using ellipse fitting and CNNs to identify and classify sushi dishes from real images, improving billing accuracy in conveyor belt sushi restaurants.

Contribution

It introduces a novel combination of ellipse detection and neural networks for real-world sushi dish recognition and pricing automation.

Findings

Ellipse detection precision of 85%

Recall of 96% in detection

Classification accuracy of 92%

Abstract

In conveyor belt sushi restaurants, billing is a burdened job because one has to manually count the number of dishes and identify the color of them to calculate the price. In a busy situation, there can be a mistake that customers are overcharged or under-charged. To deal with this problem, we developed a method that automatically identifies the color of dishes and calculate the total price using real images. Our method consists of ellipse fitting and convol-utional neural network. It achieves ellipse detection precision 85% and recall 96% and classification accuracy 92%.