Image retrieval method and server

An image retrieval and server technology, applied in the communication field, can solve problems such as inability to quickly retrieve images

Active Publication Date: 2017-06-23
XIAN UNIVIEW INFORMATION TECH CO LTD
View PDF5 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The present invention provides an image retrieval method to solve the problem in the prior art that images cannot be quickly retrieved while ensuring accuracy. The method is applied to an image retrieval server and includes the following steps:

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 and server
  • Image retrieval method and server
  • Image retrieval method and server

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0055] As mentioned in the background art, the acceleration schemes proposed for image retrieval in the prior art have the defects of decreased accuracy or high operation process. In view of this, this application proposes an image retrieval method, which uses clustering technology to quickly screen similar image subsets, reduce the number of feature comparisons, and effectively improve retrieval efficiency.

[0056] Such as figure 1 As shown, it is a schematic flow chart of an image retrieval method proposed in this application, including the following steps:

[0057]S101. Generate a first number of clustering layers according to the original features of all images in the image library, each of the clustering layers includes a second number of clusters, and the clustering layers are ranked before a threshold according to the ranking of the original features Orthogonal features corresponding to the eigenvalues ​​of are decomposed and generated sequentially, and the eigenvalue...

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. The method comprises the following steps of: previously generating a first quantity of cluster layers according to original features of all the images in an image library; when a to-be-queried image is received, extracting a first quantity of sub-features according to comparison features of the to-be-queried image; setting clusters close to corresponding sub-features in each cluster layer a special clusters; screening candidate images according to the special clusters and clusters, corresponding to each image, in each cluster layer; and finally carrying out linear search on the original features of the candidate image according to the comparison features of the to-be-queried image, so as to determine images similar to the to-be-queried image. According to the method, the linear search range of the original features is greatly decreased under the condition of ensuring the retrieval precision, the linear search time consumption is remarkably reduced and the retrieval efficiency is effectively improved.

Description

technical field [0001] The invention relates to the field of communication technology, in particular to an image retrieval method. The present invention also relates to a server. Background technique [0002] Content-based image retrieval is a technique for retrieving images based on their visual content, which mainly includes two processes of feature extraction and feature similarity matching. As the technology is becoming more and more mature, image retrieval technology has more and more applications in fields such as face comparison and vehicle search. [0003] With the collection and analysis of massive image data, the size of the image database is also becoming larger and larger, which puts forward higher and higher requirements for retrieval efficiency. In order to speed up image retrieval, in the prior art, the feature space is usually decomposed into the Cartesian product of multiple low-dimensional subspaces, and then each subspace is quantized separately, and the...

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
CPCG06F16/583G06F18/23213
Inventor 胡来丰
Owner XIAN UNIVIEW INFORMATION TECH CO LTD
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