Supercharge Your Innovation With Domain-Expert AI Agents!

A food image segmentation method

A technology for image segmentation and food, which is applied in image analysis, image enhancement, image data processing, etc., and can solve problems such as inability to segment food images

Active Publication Date: 2019-03-19
广州市派客朴食信息科技有限责任公司
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to provide a food image segmentation method, which aims to solve the problem that the current image segmentation technology cannot perform accurate image segmentation on food placed in dishes such as dishes

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 food image segmentation method
  • A food image segmentation method
  • A food image segmentation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0014] according to figure 1 As shown, a food image segmentation method includes the following steps: S1, acquire and process the image, and initially extract the edge of the dinner plate; S2, analyze the initially obtained edge of the dinner plate, and determine the missing category of the initially obtained edge of the dinner plate, If a single edge is missing, go to step S3, and if multiple edges are missing, go to step S4; S3, process the edge of the plate initially extracted, determine the center of the plate, and repair the edge symmetrically; S4, process the edge of the plate initially extracted , determine where the edge is missing, and cut the edge. The present invention determines which edge loss it belongs to by analyzing the initially extracted edge of the dinner plate, adopts different segmentation methods for different edge loss, and does not perform a single repair process, but performs a repair on the edge of the dinner plate according to the actual situation. ...

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 food image segmentation method which comprises the following steps of (S1) acquiring and processing an image and initially extracting the edge of a dinner plate, (S2) analyzing the initially obtained edge of the dinner plate and determining the missing category of the initially obtained dinner plate edge, going to step (S3) if the missing category is single-edge missing,and going to step (S4) if the missing category is multi-edge missing, (S3) processing the initially obtained dinner plate edge, determining the center of the dinner plate, and symmetrically repairingthe edge, and (S4) processing the initially obtained dinner plate edge, determining the position of the edge missing, and cutting the edge. According to the method, through analyzing the initially obtained dinner plate edge and determining the missing category to which the edge missing belongs, different cutting modes are used for different edge missing, the dinner plate edge is repaired and cut according to actual conditions, rather than single repair processing, more accurate image cutting is ensured, and the problem that foods placed in a dish can be not accurately segmented by the existingimage segmentation technology is solved.

Description

technical field [0001] The invention relates to an image segmentation method, in particular to an object image segmentation method. Background technique [0002] With the development of intelligent recognition, image segmentation technology has been applied in a wide range of fields as a basic method for extracting image elements. Existing image segmentation methods are mainly divided into threshold-based segmentation methods, region-based segmentation methods, edge-based segmentation methods, and specific theory-based segmentation methods. The threshold segmentation algorithm performs segmentation by determining the threshold and comparing the threshold with the gray value of the pixel point one by one. The region segmentation algorithm needs to select a group of seed pixels that can correctly represent the desired region, determine the similarity criterion during the growth process, and formulate the conditions or criteria for stopping the growth. Edge detection is based...

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): G06T7/12G06T7/181
CPCG06T7/12G06T7/181G06T2207/10004
Inventor 陈晓鹏杨德顺
Owner 广州市派客朴食信息科技有限责任公司
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