Web portrait search method for fusing text semantic and vision content

A text and visual technology, applied in the field of portrait retrieval, can solve the problem of immature image search engine technology, and achieve the effect of excellent retrieval performance and excellent accuracy.

Inactive Publication Date: 2009-03-18
BEIJING JIAOTONG UNIV
View PDF0 Cites 30 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0016] Generally speaking, the current content-based image search engine technology is still quite immature, and there are many theoretical and practical problems to be solved urgently, especially in image feature description, universal design, system performance optimization and practical use on the Internet, etc. still remains a subject of research

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
  • Web portrait search method for fusing text semantic and vision content
  • Web portrait search method for fusing text semantic and vision content
  • Web portrait search method for fusing text semantic and vision content

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] For the specific application background of the Web, text-based image retrieval avoids the problem of identifying complex visual elements to a certain extent. , but because it is still limited within the scope of text retrieval and describes images through index vocabulary, it is prone to problems such as subject ambiguity, inconsistent indexing, and inability to understand image content. On the contrary, content-based image retrieval mainly uses the analysis of the characteristic elements of intuitive images to index images, which has a certain degree of objectivity, such as the color histogram of each image is determined. However, the algorithm of content-based image retrieval is complex and the implementation cost is high. Therefore, in the present invention, we combine text and visual features to implement a prototype system for Web portrait image retrieval. The specific steps are as follows:

[0034] Step 1 Web crawling to form a local original image library

[0...

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 Web portrait retrieval method fused with text semantics and visual content, which comprises steps of submitting 'a query string'to a commercial search engine server to realize functions of connecting and downloading based on a HTTP protocol, downloading picture output of the commercial picture search engine and relevant websites to be a local image library, and simultaneously, extracting key tags of original websites to form XML files for post text processing, further, utilizing the AdaBoost face detection technique, mining the high-level semantics of vector models to webpage scripts containing pictures, comparing via using experienced weights and a method of dynamically weighting based on PLSA, dynamically combining visual analysis results of image characteristics and text analysis results of image characteristics via a regulating factor, obtaining rank values of relevancy of images and query, reordering the image output list of the search engine and feeding it back to users. The method has higher precision rate which is greatly increased after fusion of the characteristics.

Description

technical field [0001] The invention relates to a portrait retrieval method, in particular to a Web retrieval method integrating text semantics and visual content. The invention takes Web portrait picture retrieval in Internet environment as the object, conducts in-depth research on fusion technology of Web text semantic mining and image visual content discrimination, and realizes a prototype system of Web portrait picture retrieval in Internet environment. Background technique [0002] With the continuous development of computer technology, network technology and large-capacity storage technology, as well as the popularization of personal computers and digital camera equipment, the amount of multimedia information available on the Internet is also increasing at an alarming rate. and the richness of information contained therein, are widely used and uploaded to the Internet. The surge of information on the Internet has brought challenges to users while providing users with ...

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): G06F17/30
Inventor 赵耀谢琳朱振峰
Owner BEIJING JIAOTONG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap