Supercharge Your Innovation With Domain-Expert AI Agents!

A multi-source two-stage dish recognition method based on visual detection and re-recognition

A visual detection and re-recognition technology, applied in the field of computer vision and pattern recognition, can solve problems such as category uncertainty, attitude change, inter- and intra-class similarity interference, etc., to improve robustness and accuracy, and enhance discriminative power. and accuracy, and the effect of improving discrimination

Active Publication Date: 2022-04-29
GUANGXI NORMAL UNIV +1
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, some challenging factors in actual application scenarios, such as category uncertainty, partial occlusion, inter-class and intra-class similarity interference, pose changes, and illumination changes, still make the large-scale application and reach of dish recognition algorithms Industry standard application faces many difficulties

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
  • A multi-source two-stage dish recognition method based on visual detection and re-recognition
  • A multi-source two-stage dish recognition method based on visual detection and re-recognition
  • A multi-source two-stage dish recognition method based on visual detection and re-recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0042] refer to Figure 5 , a multi-source two-stage dish recognition method based on computer vision detection and re-identification, including a training process and a testing process, wherein the training process includes the following steps:

[0043] 1-1) Establish a dinner plate detection data set: such as image 3 As shown, the plate detection data set is collected in different real restaurants and cafeteria environments. The plate on the tray in each picture in the plate detection data set contains different dishes, or other items other than dishes, or empty space. Dinner plate, the picture of the dinner plate is collected from a vertical downward perspective, and the collected image is marked, including the rotation angle of the rectangular border of the captured image, the color of the plate, the shape of the plate, and the name of the dish. The plate detection data set is divided into a training set and a test set. The types of dishes in the test set are not include...

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 multi-source two-stage dish recognition method based on visual target detection and re-recognition. The method includes a training process and a testing process. This method locates and recognizes dishes by combining object detection and re-identification techniques, which can improve the robustness and accuracy of actual dish recognition.

Description

technical field [0001] The present invention relates to computer vision and pattern recognition technology in the field of information technology, in particular to a multi-source two-stage dish recognition method based on visual detection and re-recognition. Background technique [0002] Restaurants and canteens are places where people eat in daily life, but the traditional cash register and checkout process in restaurants and canteens is a time-consuming and laborious process, and due to the limited energy of cashiers, they cannot always work efficiently and without making mistakes. In addition, when the passenger flow During the surge, the speed of cash register and checkout has become a major bottleneck in the operating efficiency of the cafeteria. In addition, a large number of constantly updated dishes also make it difficult for cashiers to settle accurately, so manual checkout alone is far from enough Without the rapid growth of application demand, restaurants and cafe...

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 Patents(China)
IPC IPC(8): G06V10/764G06K9/62G06N3/04G06V10/774G06V10/44
CPCG06V10/44G06N3/045G06F18/241G06F18/214
Inventor 钟必能程思远李先贤刘昕
Owner GUANGXI NORMAL UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com