Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Food material identification method suitable for embedded equipment

An embedded device and recognition method technology, which is applied in the field of food recognition of embedded devices, can solve the problems of low recognition efficiency and high complexity, achieve the effect of improving detection speed, improving accuracy, and meeting real-time detection requirements

Inactive Publication Date: 2021-04-23
GUANGDONG UNIV OF TECH
View PDF6 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to overcome the technical defects of high complexity and low recognition efficiency in the application process of the existing food recognition model based on deep convolutional neural network, the present invention provides a food recognition method suitable for embedded devices

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
  • Food material identification method suitable for embedded equipment
  • Food material identification method suitable for embedded equipment
  • Food material identification method suitable for embedded equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0043] The embodiment of the present invention relates to a food recognition method suitable for embedded devices, including: acquiring images, and setting AnchorBox parameters using the K-Means algorithm when building a benchmark network based on YOLOv3; using the Darknet-53 network as the backbone network; introducing The feature pyramid structure extracts the features of multi-scale targets; replaces the Darknet-53 network with the MobileNet network; uses DIoU-NMS to improve the NMS algorithm, obtains the improved YOLOv3 model, and transplants the model to the embedded device. Input pictures into the type equipment to identify the food target.

[0044] More specifically, such as figure 1It is a schematic structural flow chart in the embodiment of the present invention. Before the training, firstly collect pictures of various food materials through crawler technology or on-site photography, select photos suitable for the data set as the initial sample data set, process the ...

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

Disclosed is a food material identification method suitable for embedded equipment, a backbone network Darknet-53 of YOLOv3 is replaced with a lightweight network MobileNet, a DIOU-NMS algorithm is adopted to replace a traditional NMS algorithm, the detection speed is greatly increased while multi-class detection of food materials is met, and the real-time detection requirement of the food materials is met; and while the real-time detection requirement is met, the detection accuracy is improved, and the detection accuracy requirement is met. The rapid transplantation of the detection model between the server and the embedded platform is realized, so that the detection performance of the detection model on miniaturized equipment (especially mobile equipment) based on an embedded system can be effectively ensured, and the method has a wider application prospect.

Description

[0001] The present invention relates to the technical field of computer and deep learning, and more specifically, relates to a food identification method suitable for embedded devices. Background technique [0002] With the continuous improvement of living standards due to social development, people's requirements for basic necessities of life are gradually increasing. Eating is an important aspect that reflects the quality of life. The so-called food is the most important thing for the people. People are no longer satisfied with the dishes they eat every day and start to pay attention to the diversification of diet. The rapid development of the logistics field provides a material basis for this. , People can come into contact with a wider variety of ingredients, the types of ingredients, what kind of ingredients they are, and what dishes this ingredients can cook, basically through human experience. Therefore, people can make life more convenient through the identification of...

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
IPC IPC(8): G06K9/00G06K9/62G06N3/04
CPCG06V20/10G06V20/68G06N3/045G06F18/214
Inventor 曾碧黄颖康
Owner GUANGDONG UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com