DCNN-based food image recognition method and system and food calorie calculation method

A recognition method and food technology, applied in the field of image recognition, can solve the problems of inaccurate food image classification, slow speed, low accuracy rate, etc.

Inactive Publication Date: 2020-01-17
BEIJING YINGPU TECH CO LTD
View PDF10 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] However, the above three methods still have the following technical problems: that is, the feature extraction speed of the above-mentioned food image recognition method is relatively slow when training the recognition model, and the classification of food images by using the trained recognition model is not accurate enough, and the accuracy rate is not high enough. high

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
  • DCNN-based food image recognition method and system and food calorie calculation method
  • DCNN-based food image recognition method and system and food calorie calculation method
  • DCNN-based food image recognition method and system and food calorie calculation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0062] In one embodiment of the present invention, a deep convolutional neural network (DCNN) is used to recognize food images. Since the recognition of food images is a fine-grained visual recognition, it is a relatively difficult problem compared with traditional image recognition. In order to solve this problem, this embodiment recognizes the types of food images based on the DCNN deep convolutional neural network, and this method can accurately identify food images; moreover, the food image method based on the DCNN deep neural network is very suitable for large-scale images Data, this is because it only takes 0.03 seconds to classify a food photo using GPU (Graphics Processing Unit, image processor), so the recognition efficiency is very high.

[0063] figure 1 is a schematic flowchart of a DCNN-based food image recognition method according to an embodiment of the present application. see figure 1 As known, the DCNN-based food image recognition method provided by the em...

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 DCNN-based food image recognition method. The method comprises the steps of classifying collected food initial images to obtain a training data set and a test data set; constructing a DCNN deep convolutional neural network by using the training data set, and training the DCNN deep convolutional neural network to generate a training model of the food image; inputting a test sample in the test data set into a training model of the food image, and judging the type of an object in the food image to generate a test result; obtaining an identification model of the food image according to a test result; and identifying the food type in the to-be-detected food image by utilizing the identification model of the food image. The invention also discloses a recognition systemand a food calorie calculation method. According to the invention, the type of the food can be quickly and accurately identified, so that a user can further judge nutrition, heat and the like contained in the food conveniently.

Description

technical field [0001] The present application relates to the field of image recognition, in particular to a DCNN-based food image recognition method and system and a food calorie calculation method. Background technique [0002] Obesity and other health problems are on the rise in today's real life. Obesity has doubled in more than 70 countries since 1980, and obesity can lead to other types of chronic diseases such as heart disease, diabetes, arthritis, and more. Therefore, people nowadays pay more attention to the nutritional value of food to prevent these diseases. [0003] Diet management is the key to regulating people's eating habits. If people know the nutritional information of the food they are eating, it will help people who need dietary management. Therefore, in order to obtain nutritional information about food, a food image recognition system is needed to detect the food in the image. , and then analyze the nutrition, calorie information, etc. of the food. ...

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): G06K9/62G16H20/60
CPCG16H20/60G06V20/68G06F18/24G06F18/214
Inventor 陈庶
Owner BEIJING YINGPU TECH CO LTD
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