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

Multi-feature image tag sorting method based on WordNet semantic similarity

A technology of semantic similarity and image labeling, applied in the field of Internet community image label processing, to achieve the effect of accurate sorting

Active Publication Date: 2014-05-21
BEIJING UNION UNIVERSITY
View PDF3 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The above two types of methods divide label improvement and label ranking into two different research contents to a large extent, so they seldom do too much processing on the image label itself in the process of label ranking. simple preprocessing

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
  • Multi-feature image tag sorting method based on WordNet semantic similarity
  • Multi-feature image tag sorting method based on WordNet semantic similarity
  • Multi-feature image tag sorting method based on WordNet semantic similarity

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] The present invention will be further described below in conjunction with drawings and embodiments.

[0049] The flowchart of the method of the present invention is as figure 1 shown, including the following steps:

[0050] Step 1, establish a training sample library.

[0051] Using the 269648 images in the existing database NS-WIDE to build a sample image library specially used for SVM linear classifier training, including scene image (Sense Image) and object image (Object Image).

[0052] Step 2, extract the salient region map of the image in the sample library.

[0053] Step 2.1, obtain primary visual features.

[0054] Using the existing Itti model principle method, by calculating the central peripheral differential sampling, the brightness, color and direction feature maps N(I), N(C) and N(O) are obtained respectively, and the three feature maps are combined into a saliency Regional map S.

[0055] S=α*N(I)+β*N(C)+γ*N(O)

[0056] Among them, N( ) is the norma...

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 relates to a multi-feature image tag sorting method based on WordNet semantic similarity. The multi-feature image tag sorting method includes the steps of establishing and training a specimen bank, extracting significant region graphs of images in the specimen bank, training an SVM classifier, preprocessing image tags to be tested, judging the types of the images to be tested, and sorting the image tags to be tested. The multi-feature image tag sorting method integrates correlation, visuality, multi-feature and the like, different features of an entire scene image are considered, and different features of a saliency map of an object image are also considered. Before the image tags are sorted, improvement is conducted on the problems such as incorrectness of the image tags and non-comprehensiveness of the tags, and the correlation between the image tags and image content and the correctness and the comprehensiveness of the image tags are improved; according to the multi-feature image tag sorting method, the similarity between visual features of the images is considered, and the semantic similarity between tag texts is also considered, so that sorting of the image tags is more accurate.

Description

technical field [0001] The invention belongs to the field of Internet community image label processing, and relates to a multi-feature image label sorting method based on WordNet semantic similarity by using an existing database (NS-WIDE) image and a corresponding label list. Background technique [0002] With the continuous development of Internet technology, especially the rapid development of web2.0, we have entered the information age. At the same time, the number of social networks is also increasing, and the most representative social media sites are Facebook, Google's video sharing site YouTube and Yahoo's social image sharing site Flicker. This type of social networking site allows network users to upload images or videos by themselves. Users can mark the content, time, location and other information of the image through keywords. These marked information are called "tags (Tag)", and for The process of adding keyword tags to media is called "Tagging". Since most In...

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): G06F17/30G06K9/62
CPCG06F16/58G06F18/24
Inventor 刘宏哲袁家政吴焰樟王棚飞
Owner BEIJING UNION UNIVERSITY
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