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

An automatic image tagging method based on inter-word correlation

An image automatic tagging and correlation technology, applied in the field of image processing, can solve the problems of semantic inconsistency of tagged words, ignore the correlation between words, etc., reduce the impact, improve the recall rate and precision rate, and improve the overall tagging effect Effect

Active Publication Date: 2017-01-25
BEIJING JINGDONG SHANGKE INFORMATION TECH CO LTD +1
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] In view of this, the present invention provides a kind of image automatic tagging method based on inter-word correlation, to overcome the defect that the joint media correlation model image automatic tagging algorithm thinks that different candidate tagged words are independent of each other in the tagging process, Solve the problem of semantic inconsistency between tagged words in tagging results due to ignoring inter-word correlation

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 automatic image tagging method based on inter-word correlation
  • An automatic image tagging method based on inter-word correlation
  • An automatic image tagging method based on inter-word correlation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] In order to make the object, technical solution and advantages of the present invention more clearly, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0029] Technical scheme of the present invention is:

[0030] A. According to the formula Calculate the semantic vector of each labeled word w in the training set T, and express the labeled word w as a vector form w=1 ,v 2 ,...,v m >, where c i is a contextual linking word, there are m contextual linking words, p(c i ) is the contextual linker c i The overall distribution probability of , p(c i / w) means contextual correlative word c i and the ratio of the number of co-occurrences of the tag word w in the training set T to the total number of times the tag word w appears in the training set T, that is Wherein, the context-related words are tagged words in the training set T;

[0031] B. According to the formula Calculate t...

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 automatic labeling method based on inter-word correlation. The training set T contains l images, and each image in the training set T is marked with n labeled words, and has corresponding visual lemmas. Labeling the image as I, the method includes: calculating the semantic vector of each labeling word w according to the formula, and expressing the labeling word w as a vector form w=<v1,v2,...,vm>, wherein, ci is a context-related word, and there are m context associated words; calculate the semantic similarity between tagged words according to the formula, where |||| For the number of marked phrases; Calculate the conditional probability p (I / wi) according to the formula; Calculate p (I / A) according to the formula; Calculate the annotation of the image I to be marked by the formula A=arg maxAp (I / A)p (A) Phrase A.

Description

technical field [0001] The invention relates to the field of image processing, in particular to an image automatic labeling method based on inter-word correlation. Background technique [0002] With the rapid development of multimedia and Internet technology, people's daily life and work rely more and more on multimedia information such as images. Semantic-based image retrieval can not only accurately express the user's retrieval intention, but also facilitate the user's use. Therefore, this retrieval method has not only become an important form of image retrieval, but also has become a technical hotspot pursued by researchers. [0003] The automatic image annotation technology is an important and challenging task in image semantic retrieval. The emergence of image automatic annotation technology is to automatically obtain the semantic information contained in the visual content of the image. Build a bridge between them to support semantic retrieval at the semantic level. ...

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): G06F17/30
CPCG06F16/58G06F18/2155
Inventor 安震
Owner BEIJING JINGDONG SHANGKE 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