Sushi Dish - Object detection and classification from real images
This solves a specific billing inefficiency for sushi restaurants, but it is incremental as it applies existing techniques like ellipse fitting and CNNs to a new domain.
The paper tackles the problem of manual billing in conveyor belt sushi restaurants by developing an automated method to identify dish colors and calculate total prices from real images, achieving 85% precision and 96% recall for ellipse detection and 92% accuracy for classification.
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%.