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

Image retrieval method based on BoVW (Bag of Visual Words) optimization and query expansion

A visual dictionary, query expansion technology, applied in character and pattern recognition, special data processing applications, instruments, etc., can solve problems such as poor anti-interference ability and low retrieval accuracy

Inactive Publication Date: 2016-11-23
HUAQIAO UNIVERSITY
View PDF7 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The present invention overcomes the problems of low retrieval accuracy and poor anti-interference ability in the current image retrieval in the prior art, and provides an image retrieval method based on visual dictionary optimization and query expansion for the purpose of improving image retrieval accuracy

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
  • Image retrieval method based on BoVW (Bag of Visual Words) optimization and query expansion
  • Image retrieval method based on BoVW (Bag of Visual Words) optimization and query expansion
  • Image retrieval method based on BoVW (Bag of Visual Words) optimization and query expansion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0060] Specifically, the invention will be described in three parts as follows, including: implementation premise, detailed implementation mode, specific operation process and specific examples. The premise of the first part includes the establishment of a visual dictionary model; the second part corresponds to the steps of the present invention, giving the overall process and the specific operation method of each step; the third part gives a specific example and analyzes the obtained results.

[0061] 1. Building a visual dictionary model

[0062] An image has hundreds or thousands of local features. If an index is built with a single local feature as a unit, all local features need to be matched one by one during retrieval. This not only greatly increases the retrieval time overhead, but also affects the practicability of the system. . In order to reduce the time cost of image retrieval, Sivic et al. proposed a visual dictionary method (Bag of Visual Words, BoVW) by referri...

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 retrieval method based on BoVW (Bag of Visual Words) optimization and query expansion. The image retrieval method comprises: extracting SIFT features of a training image, and carrying out clustering on the SIFT features by utilizing a density-based clustering method to generate a BoVW set; analyzing correlation of visual words and a target category by a chi-square model, and simultaneously, filtering out a certain number of visual stop words by combining word frequencies of the visual words; carrying out mapping matching on the SIFT features and an optimized BoVW to obtain a visual word histogram; carrying out similarity matching on a visual word histogram of an query image and the visual word histogram of the training image, and according to a primary matching result, carrying out secondary or repeated retrieval by combining a query expansion strategy so as to obtain a final retrieval result. The invention provides the image retrieval method based on BoVW optimization and query expansion, which aims to improve image retrieval accuracy.

Description

technical field [0001] The invention relates to an image retrieval method, in particular to an image retrieval method based on visual dictionary optimization and query expansion. Background technique [0002] The visual dictionary method (Bag of Visual Words, BoVW) quantifies the local features of the image into word frequency vectors for retrieval through the visual dictionary, which can not only use the local information of the image, but also achieve a faster speed than the direct retrieval of local features, and has become the current image retrieval method. mainstream method. However, the image retrieval method based on BoVW has the following problems: First, the current clustering algorithm for generating visual dictionaries has low time efficiency and a large amount of calculation, which makes it difficult for BoVW to be applied to large-scale data sets; second, due to the limitations of clustering algorithms and image The existence of background noise causes visual ...

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): G06F17/30G06K9/62
CPCG06F16/583G06F18/23
Inventor 李弼程柯圣财赵永威杜吉祥刘海建
Owner HUAQIAO UNIVERSITY
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