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

Image retrieval method based on vocabulary tree information fusion and Hausdorff distance combination

An image retrieval and vocabulary tree technology, which is applied in still image data retrieval, still image data clustering/classification, special data processing applications, etc., can solve the problems of complex retrieval process and imperfect method system development.

Inactive Publication Date: 2017-06-13
HARBIN UNIV OF SCI & TECH
View PDF10 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Semantic-based image retrieval is to further refine its high-level semantic expression ability on the basis of image visual features, but the retrieval process of this type of retrieval method is complicated, and there are problems that the development of the method system is not yet perfect;

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 vocabulary tree information fusion and Hausdorff distance combination
  • Image retrieval method based on vocabulary tree information fusion and Hausdorff distance combination
  • Image retrieval method based on vocabulary tree information fusion and Hausdorff distance combination

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment 1

[0074] This embodiment is a theoretical embodiment of an image retrieval method based on the combination of vocabulary tree information fusion and Hausdorff distance.

[0075] The image retrieval method based on the combination of vocabulary tree information fusion and Hausdorff distance in this embodiment, the flow chart is as follows figure 1 As shown, the method includes the following steps:

[0076] Step a, extracting the image to be retrieved and the SIFT feature of the image library;

[0077] Step b, generate SIFT descriptor histogram and SIFT descriptor kernel density;

[0078] Step c, fusing the SIFT descriptor kernel density and the SIFT descriptor histogram;

[0079] Step d, improving the traditional Hausdorff distance measure;

[0080] Step e, using the improved Hausdorff distance for image matching.

[0081] The above-mentioned image retrieval method based on the combination of vocabulary tree information fusion and Hausdorff distance, the specific steps of ste...

specific Embodiment 2

[0127] This embodiment is a theoretical embodiment of an image retrieval method based on the combination of vocabulary tree information fusion and Hausdorff distance.

[0128] In view of the fact that most of those skilled in the art are academics, they are more accustomed to writing technical documents in the way of writing articles. Therefore, on the basis of no essential difference from the first embodiment, the second embodiment is supplemented according to academic habits.

[0129] The image retrieval method based on the combination of vocabulary tree information fusion and Hausdorff distance of the present embodiment includes the following steps:

[0130] Step a: SIFT feature extraction of the image to be retrieved and the image database (SIFT: Scale Invariant Feature Transform)

[0131] Step a1: Construct the image to be retrieved and the image library Gaussian difference scaling function

[0132] During SIFT descriptor extraction, the Gaussian difference scale space i...

specific Embodiment 3

[0173] This embodiment is an experimental embodiment of an image retrieval method based on the combination of vocabulary tree information fusion and Hausdorff distance.

[0174] figure 2 The precision rate of image retrieval based on SIFT descriptor histogram, image retrieval based on SIFT descriptor kernel density and image retrieval based on the present invention is given.

[0175] From figure 2 It can be seen from the figure that the first four items in the image category are clouds, stars, birds, and trees with a simple background, and the precision rates of the three retrieved images are not much different; the last four items in the image category are tiger, fish, Mountains and flowers are pictures with complex backgrounds, and the precision rates of the three retrieval methods are very different, and the retrieval of the present invention is far greater than the retrieval of the first two.

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 provides an image retrieval method based on vocabulary tree information fusion and Hausdorff distance combination and belongs to the technical field of image retrieval. The image retrieval method comprises the steps that firstly, images to be retrieved and SIFT characteristics of an image library are extracted, an SIFT descriptor histogram and SIFT descriptor kernel density are generated, then the SIFT descriptor kernel density and the SIFT descriptor histogram are fused, and finally an improved Hausdorff distance is used for image matching by improving traditional Hausdorff distance measure. The image retrieval method includes information fusion of extensible vocabulary trees based on SIFT kernel density and extensible vocabulary trees based on the SIFT histogram, the improved Hausdorff distance in image similarity measurement standard and combination of information fusion and the improved Hausdorff distance. Experiments show that the method can not only improve the image retrieval accuracy and is applicable to retrieval of images with complex backgrounds.

Description

technical field [0001] The invention relates to an image retrieval method based on the combination of vocabulary tree information fusion and Hausdorff distance, which belongs to the technical field of image retrieval. Background technique [0002] Since the image retrieval method came into being, three important branches have been formed: text-based image retrieval, content-based image retrieval and semantic-based image retrieval. [0003] Text-based image retrieval uses text such as image names and image features to describe user needs, but due to the limitation of text expression ability and the ambiguity of text annotation, the retrieval results often do not match user needs; [0004] Semantic-based image retrieval is to further refine its high-level semantic expression ability on the basis of image visual features, but the retrieval process of this type of retrieval method is complicated, and there are problems that the development of the method system is not yet perfect...

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
CPCG06F16/583G06F16/55G06V10/462G06V10/44G06F18/23213G06F18/25
Inventor 孙晓明张宁车畅刘野吴海滨
Owner HARBIN UNIV OF SCI & TECH
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