Dish identification method, cashier method, dish order urging method and related device

Abstract

The invention discloses a dish identification method, a cashier method, a dish order urging method, a related device, computing equipment and a medium. The dish recognition method comprises the stepsthat a dish image to be recognized is input into a first dish category recognition model to be processed so as to obtain image features output by a bottleneck layer in the first dish category recognition model, and the bottleneck layer comprises all processing layers in front of the last processing layer in the first dish category recognition model; and inputting the image features into a second dish category identification model for identification so as to obtain the category of the dish in the dish image.

Description

technical field [0001] The invention relates to the technical field of image processing, and in particular to a dish recognition method, a cash register method, a dish reminder method, related devices, computing equipment and media. Background technique [0002] When eating in a restaurant, we often hope that the merchant can provide services such as ordering, serving and checking out quickly, so as to avoid unnecessary waste of time. However, during the peak dining period, especially for the canteen, due to the large flow of people, the manpower cannot bear the current work intensity, which makes it difficult for the service to meet the above requirements. Various problems such as waiting time for serving food and long time for bill settlement bring poor dining experience. Among them, the waiting time for serving food and the long time for bill settlement are the most common problems. [0003] In order to solve such problems, the self-service cashier robot can be used to ...

AI Technical Summary

Problems solved by technology

[0004] However, the existing dish recognition methods implemented by deep neural network, on the one hand, need to collect a large number of actual dish samples in order to train the deep neural network; The structure of the network will be more complex and the number of layers will be more. In this case, the training time will be longer. Even if the trained deep neural network can achieve a better recognition effect, it may also appear in the actual application of dish recognition. The problem of slow recognition response due to the complex network structure also cannot provide a good user experience. Therefore, it is necessary to provide a new dish recognition method to optimize the above processing process

Images