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

Image area labeling method based on visual semantic relation graph

A technology of image region and semantic relationship, applied in the field of image semantic understanding, can solve problems affecting the accuracy of image region labeling algorithms

Active Publication Date: 2018-04-27
EAST CHINA UNIV OF SCI & TECH
View PDF4 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] The amount of image data in today's society is huge, and image automatic labeling technology has become an important way for people to retrieve and manage image data. However, due to the existence of the "semantic gap", the accuracy of traditional image region labeling algorithms has been seriously affected. This invention proposes a Image Region Labeling Method Based on Visual Semantic Relationship Graph

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
  • Image area labeling method based on visual semantic relation graph
  • Image area labeling method based on visual semantic relation graph
  • Image area labeling method based on visual semantic relation graph

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0018] The technical solution of the present invention will be specifically described below in conjunction with the accompanying drawings.

[0019] figure 1 It is a schematic flowchart of an image region labeling method based on a visual semantic relationship graph provided by the present invention, and the labeling method includes 4 units.

[0020] Unit 100 is the construction of the image global similarity subgraph and the image region similarity subgraph. Taking the image as a unit, extract the global visual features of the image: SIFT feature, HSVH feature, color moment feature and Gabor feature, and use the bag of words model to represent the image content. Use Euclidean distance to calculate the correlation of global visual features between images to obtain a global similarity subgraph, such as image 3 shown. Taking the image area as a unit, extract the visual features of the image area: HSVH feature, color moment feature and Gabor feature, and use the bag of words m...

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 an image labeling algorithm based on a visual sense and semantics and the algorithm can be used to realize automatic labeling of an image area. An image area labeling algorithmbased on a visual semantic relation graph comprises two portions: construction of the visual semantic relation graph and image labeling based on the visual semantic relation graph. In the visual semantic relation graph construction, a global similarity and an area similarity among images, semantic association of image area labels and association among levels are considered. On the constructed visual semantic relation graph, semi-supervised learning is performed, an association degree between an unlabeled image area and the image area labels is acquired and label prediction is performed on theunlabeled image area.

Description

technical field [0001] The invention belongs to the field of image semantic understanding, and in particular relates to an image region labeling method based on a visual semantic relationship graph. Background technique [0002] The amount of image data in today's society is huge, and image automatic labeling technology has become an important way for people to retrieve and manage image data. However, due to the existence of the "semantic gap", the accuracy of traditional image region labeling algorithms has been seriously affected. This invention proposes a Image Region Labeling Method Based on Visual Semantic Relationship Graph. [0003] There are image visual feature similarities between images globally, image visual feature similarity between image regions, and semantic correlation between image tags. These information are helpful for image region labeling and understanding. Therefore, the present invention proposes a A visual-semantic relationship diagram that effectiv...

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): G06K9/62G06K9/46
CPCG06V10/56G06V10/462G06F18/24
Inventor 张静陶提穆亚昆王喆赵贤文陈美
Owner EAST CHINA UNIV OF SCI & 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