Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Multi-feature adaptive fusion-based image retrieval method

An image retrieval and self-adaptive technology, applied in special data processing applications, instruments, electrical digital data processing, etc., can solve problems such as inability to automatically analyze the retrieval effect, and achieve the effect of improving the effect and accuracy

Inactive Publication Date: 2011-09-14
宋金龙 +1
View PDF3 Cites 29 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

A lot of work has also been done on feature fusion, but most of these works are based on linear weighting of features. For all retrieved images, the weights of each feature are fixed, and the retrieval effect of each feature cannot be automatically analyzed to perform dynamic fusion.

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 adaptive fusion-based image retrieval method
  • Multi-feature adaptive fusion-based image retrieval method
  • Multi-feature adaptive fusion-based image retrieval method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] Such as figure 1 , 2 As shown, the image retrieval method based on multi-feature adaptive fusion includes the following steps:

[0030] A. Selection of image features: such as figure 1 As shown, in the offline training phase, point-based SURF features and region-based HOG features are extracted for each image in the image library; the selected features must have certain complementarity in describing the image content.

[0031] B. Extract SURF and HOG features from database images, cluster using hierarchical kmeans algorithm, and construct SURF semantic tree and HOG semantic tree (Vocabulary tree), such as image 3 As shown, the square represents the semantic tree formed by SURF features, and the triangle represents the semantic tree formed by HOG features.

[0032] C. If figure 2 As shown, in the online retrieval stage, the SURF feature and HOG feature are extracted for the image input by the user and need to be retrieved. According to the retrieval method of the ...

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 a multi-feature adaptive fusion-based image retrieval method. The method comprises the following steps of: selecting image features, namely extracting more than two image features of each image in an image library; establishing a semantic tree of each image feature of each image in the image library; performing normalization processing on all image features of the images which is input by a user and is to be retrieved; performing fusion on the scores of the retrieval results of all image features; in screened images, respectively weighting and adding the scores of the retrieval results of all image features of each image to obtain final scores of the retrieval results; and outputting the images according to an order of the final scores of the retrieval results from high to low, wherein the score weights of the retrieval results of each image feature are not fixed. Due to the adoption of the multi-feature fusion method, the retrieval accuracy is greatly improved; and due to the adoption of a dynamic weight, a traditional fixed weight is changed, and the effect of image retrieval is further improved.

Description

technical field [0001] The invention relates to an image retrieval method, in particular to an image retrieval method based on multi-feature adaptive fusion. Background technique [0002] In the existing image retrieval methods, the content-based image retrieval technology extracts the features that the user is interested in in the image, including some visual features such as color, shape, texture, etc. Retrieval realizes the retrieval of real image visual content features. This retrieval method is a major breakthrough in "finding pictures with keywords". With the development of content-based image retrieval technology, there have been many image retrieval systems. Although the fields or functions of the image retrieval system are various, the basic retrieval method includes the following steps: extracting image features and writing them into the corresponding image library; extracting features from the image input by the user and comparing them with the features in the i...

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 宋金龙张小军
Owner 宋金龙
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
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