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

An image automatic annotation method based on web social media

An automatic image annotation and image technology, which is applied in the field of automatic image annotation based on Web social media, can solve the problem of not being able to annotate a large number of network images, and achieve the effect of narrowing the semantic gap and quickly annotating

Active Publication Date: 2017-05-31
YANGZHOU RUIFENG INFORMATION TECH CO LTD
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the past, researchers mainly focused on automatic image labeling from the perspective of machine learning. The automatic image labeling method based on machine learning requires a large number of parameter optimization and complex learning processes, and cannot quickly and effectively label a large number of network pictures.

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
  • An image automatic annotation method based on web social media
  • An image automatic annotation method based on web social media
  • An image automatic annotation method based on web social media

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] The present invention will be further described according to the following specific embodiments

[0020] An image automatic labeling method based on Web social media, the steps are as follows:

[0021] Step 1: First, the randomly selected Web-based image is divided into blocks according to the needs of the setting by the image processing tool. The number of regional blocks obtained after the regional division is 1000, and each regional block is divided into K h It means that h is a natural number less than or equal to 1000;

[0022] Step 2: Then use the R component value, the G component value and the B component value of the color gamut determined by the RGB three primary colors to form a color gamut element, and the color gamut element is expressed as T(L)={T R (L), T G (L), T B (L)},T R (L), T G (L) and T B (L) are respectively expressed as R component value, G component value and B component value, thus obtaining each area block K h The R component attribute,...

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

An automatic image labeling method based on Web social media comprises the steps of firstly using an image processing tool to divide a Web-based image into blocks according to the set areas required to be divided, then sequentially performing determination on R component attribute, G component attribute and B component attribute of each area block Kh, determining relative transverse displacement attribute and relative longitudinal displacement attribute, determining outline attribute, and finally performing image labeling by adopting a multi-class labeling and classifying method. 'Semantic gaps' can be effectively decreased, and a large amount of network pictures can be quickly and effectively labeled.

Description

technical field [0001] The invention belongs to the technical field of automatic image labeling, and relates to an automatic image labeling method based on Web social media. Background technique [0002] In content-based image retrieval, there is a "semantic gap" between the original underlying features of the image and the deep semantics abstracted by the user. The current method of narrowing the "semantic gap" is not ideal. With the development of Web 2.0, more and more Internet users will attach corresponding text information to describe or explain the pictures when uploading pictures to the Internet. This information plays an important role in analyzing the semantic content of images and mining image retrieval user intentions. In the past, researchers mainly focused on automatic image labeling from the perspective of machine learning. Automatic image labeling methods based on machine learning require a large number of parameter optimizations and complex learning process...

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): G06F17/30G06T7/90
CPCG06F16/5838
Inventor 蔡成委丁智杰丁永华
Owner YANGZHOU RUIFENG INFORMATION TECH CO LTD
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