Dish identification method and system based on Dish-YOLO

A recognition method and recognition system technology, which is applied in point-of-sale network systems, character and pattern recognition, payment architecture, etc., can solve problems such as inaccurate recognition results and inability to generate exclusive recognition models, and achieve short training time and high applicability Sex and practicality, the effect of long training time

Pending Publication Date: 2022-03-18
绍兴数鸿科技有限公司
View PDF2 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The training set required by this method to train the model is fixed, and the exclusive recognition model cannot be generated according to different users, and factors such as changes in light caused by environmental changes will also lead to inaccurate recognition results.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Dish identification method and system based on Dish-YOLO
  • Dish identification method and system based on Dish-YOLO
  • Dish identification method and system based on Dish-YOLO

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0054] In this example, the dish recognition method of Dish-YOLO shown in 1) to 3) above and the construction and use process of the system are shown, including the following steps:

[0055] 1. Restaurant model training and initial construction of cloud storage module

[0056] Step 1.1 Creation of positioning model data set and data preprocessing

[0057] In this example, the newly opened restaurant s needs to manually input the picture data of the plate Indicates the i-th image of the store numbered s used for positioning training), using the LabelImg labeling tool to label the dish area in the image to obtain Different from target detection, this method labels all dishes as the same category, namely category bowl. Such as figure 1 Shown is one of the original image samples of the dinner plate, and the image sample can be annotated to form the following figure 2 Annotated sample shown.

[0058] The original image data and label frame information used for Dish-YOLO pos...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a dish identification method and system based on Dish-YOLO, and belongs to the field of image identification. The system comprises three parts, namely a dish identification module, an auxiliary settlement and data set updating module and a model training and cloud storage module, and comprises the following steps: firstly, carrying out dish region positioning on a dinner plate picture and dish identification on a single dish picture through the dish identification module; the dish identification result and the pricing result are manually audited through an auxiliary settlement and data set updating module, and a cloud training data set is updated; and finally, cloud training is performed on the dish identification model through a model training and cloud storage module, and the dish identification model is synchronously updated to a local end of a restaurant. According to the invention, through a dish identification method of first positioning and then identification, in combination with auxiliary settlement and cloud training, deep fusion of a traditional manual cashier settlement mode and an automatic dish identification settlement mode is realized, so that the intelligent dish identification settlement system has stronger practicability and fault tolerance.

Description

technical field [0001] The invention belongs to the field of image recognition, and in particular relates to a dish recognition method and system based on Dish-YOLO. Background technique [0002] The traditional cashier work in the catering industry has the problems of many types of dishes, difficult to remember, and high repetition of work. Reform is imperative. In recent years, with the rapid development of industrial intelligence, the catering industry is gradually moving towards the road of intelligence, and many solutions for intelligent identification of dishes have gradually emerged. The intelligent identification of dishes can greatly reduce the cashier's settlement time, improve work efficiency, reduce queuing and waiting time, and thus improve profitability. From the current point of view, the solutions mainly include two categories: [0003] The first category is to add chips to the dishes and use radio frequency technology to identify the dishes and then distin...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06V10/25G06V10/764G06V10/774G06V10/776G06V10/82G06V20/68G06V10/94G06Q20/20G06Q30/02G06Q50/12G06K9/62
CPCG06Q20/208G06Q30/0283G06Q50/12G06F18/2178G06F18/214G06F18/24
Inventor 李万清张俊峰刘俊李枨唐莹
Owner 绍兴数鸿科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap