Face and name aligning method and system facing to cross media news retrieval

A cross-media and person-name technology, applied in the field of cross-media information retrieval, can solve problems such as inability to guarantee, insufficient overall correlation, and complex problems, and achieve the effect of good search ability, accurate and effective automatic face-person name alignment

Inactive Publication Date: 2012-08-08
FUDAN UNIV
View PDF3 Cites 37 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, different news face images belonging to the same person may be very different due to many factors such as light intensity, occlusion degree, face angle, etc.
Therefore, it is not sufficient to measure the overall correlation of each retrieved face set by directly measuring the similarity between these face visual features.
[0016] (4) Since aligning

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
  • Face and name aligning method and system facing to cross media news retrieval
  • Face and name aligning method and system facing to cross media news retrieval
  • Face and name aligning method and system facing to cross media news retrieval

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] (1) Name importance evaluation algorithm

[0039] The idea of ​​the name importance evaluation algorithm is based on the following assumption: in the text annotation corresponding to news images, not all names are equally important, and the importance of each name is relatively different. In general, for a name with higher importance, its corresponding face image has a higher probability of appearing in the news image related to the text. In addition, some names appearing in text annotations may not have corresponding faces in corresponding news images. Therefore, it is very necessary to evaluate the importance of each name contained in the text in the same text annotation, so as to judge which names are more likely to appear together with their corresponding face images. As the only supplementary text information of news images, this limited text annotation requires multi-level analysis to obtain effective text features, and then to effectively distinguish and measu...

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 belongs to the technical field of cross-media information retrieval and particularly relates to face and name aligning method and system based on image characteristics and text content in cross media news retrieval. In the invention, four main algorithms are included, and are name importance assessment algorithm, multimode information discovery algorithm based on web excavation, face set cohesion algorithm and multimode aligning combination optimization algorithm. In the invention, the related image characteristics and text content processing method is used, meanwhile, relative mathematical model is built, optimization to new picture search is performed, and through multi-grade and deep-level text content analyses and effective face-name alignment evaluation mechanism, and combination optimization at the aim of problems can be achieved. According to the invention, a great significance to efficient image retrieval performed under the consideration of high level semantic information of images and on the basis of large-scale and multifarious new image can be played, the retrieval relativity can be enhanced, the user experience is enhanced, and the wide application value is played in the field of medium information retrieval.

Description

technical field [0001] The invention belongs to the technical field of cross-media information retrieval, and in particular relates to a specific media-multimodal news cross-media retrieval method and system. Background technique [0002] With the popularization of the network and the popularization of image equipment, the rapidly enhanced digital acquisition technology and storage delivery capabilities have led to an explosive increase in online and offline image data, especially those news image resources with text annotations. Because the sources of such information are becoming more and more abundant, it is very important to implement more effective retrieval, organization and analysis of news image resources [1] . [0003] On the one hand, since news images and their corresponding text annotations are usually described on the subject of people, this makes it more urgent for users to query news images related to a specific person by using a complete and effective retrie...

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): G06F17/30G06F17/27G06N3/12
Inventor 张玥杰吴伟金城薛向阳
Owner FUDAN 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