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

Image search method and system

A picture search and picture technology, applied in the computer field, can solve problems such as low retrieval efficiency and increased system overhead, and achieve the effects of improving retrieval efficiency, reducing I/O access, and reducing cache requirements

Active Publication Date: 2019-11-22
SOUTH UNIVERSITY OF SCIENCE AND TECHNOLOGY OF CHINA
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the embodiments of the present invention is to provide a method and system for image search, aiming at solving the problem that the query in the image search process requires multiple I / O accesses to obtain the result due to the inability of the prior art to provide an effective image search method. The final result, resulting in low retrieval efficiency and increased system overhead

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 search method and system
  • Image search method and system
  • Image search method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0024] figure 1 The implementation flow of the image search method provided by the first embodiment of the present invention is shown. For the convenience of description, only the parts related to the embodiment of the present invention are shown, and the details are as follows:

[0025] In step S101, a picture query sample submitted by a user is received, and a feature vector of the picture query sample is extracted.

[0026] The embodiments of the present invention are applicable to image or image-based search engines or search systems, for example, image search engines or multimedia search engines. When a user submits an image query sample for image query, the image query sample (that is, the image submitted by the user) is first processed to extract a feature vector of the image query sample for subsequent search.

[0027] In step S102, the extracted feature vectors are retrieved in the index structure to obtain associated candidate identifiers.

[0028] In step S103, th...

Embodiment 2

[0034] figure 2 The implementation process of the image search method provided by the second embodiment of the present invention is shown. For the convenience of description, only the parts related to the embodiment of the present invention are shown, and the details are as follows:

[0035] In step S201, a picture query sample submitted by a user is received, and a feature vector of the picture query sample is extracted.

[0036] The embodiments of the present invention are applicable to image or image-based search engines or search systems, for example, image search engines or multimedia search engines. When a user submits an image query sample for image query, the image query sample (that is, the image submitted by the user) is first processed to extract a feature vector of the image query sample for subsequent search.

[0037] In step S202, the extracted feature vectors are retrieved in the index structure to obtain associated candidate identifiers.

[0038] In step S20...

Embodiment 3

[0053] image 3 The structure of the picture search system provided by the third embodiment of the present invention is shown. For the convenience of description, only the parts related to the embodiment of the present invention are shown, including:

[0054] Vector extracting unit 31, is used for receiving the picture query sample that the user submits, extracts the feature vector of picture query sample;

[0055] An identification obtaining unit 32, configured to retrieve the feature vector in the index structure to obtain the associated candidate identification;

[0056] A vector search unit 33, configured to search for an approximate feature vector of a picture candidate corresponding to the candidate identification in a pre-built cache histogram;

[0057] A distance calculation unit 34, configured to calculate the distance between the feature vector of the image query sample and the approximate feature vector; and

[0058] The retrieval result processing unit 35 is conf...

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 is applied to the technical field of computers, and provides an image searching method and system. The method comprises the following steps of: receiving an image inquiry sample submitted by a user, extracting a characteristic vector of the image inquiry sample, retrieving the characteristic vector in an index structure so as to obtain a related candidate identifier, searching an approximate characteristic vector of an image candidate corresponding to the candidate identifier from a pre-constructed cache histogram, calculating the distance between the characteristic vector of the image inquiry sample and the approximate characteristic vector, if the distance is less than a first pre-set threshold value, determining the image candidate as a retrieved result and outputting the candidate identifier, and, if the distance is greater than a second pre-set threshold value, abandoning the associated candidate identifier. The image retrieving efficiency is greatly increased; and simultaneously, cache demands for a retrieving system are reduced.

Description

technical field [0001] The invention belongs to the technical field of computers, and in particular relates to a picture search method and system. Background technique [0002] In the similarity search of high-dimensional data (for example, image search, multimedia retrieval, etc.), the curse of dimension makes the traditional tree index algorithm (for example: b+ tree) become very inefficient and even degenerates into a linear scan. , therefore, some researchers proposed to use high-dimensional sensitive hash algorithm for approximate search, which has been widely studied. However, whether it is a tree index algorithm or a high-dimensional sensitive hash algorithm, both focus on optimizing the process of generating candidates (candidate generation), ignoring the overhead of finding the final result (candidate refinement) from candidates . Since this process usually needs to perform multiple I / O (input / output) accesses to read data and calculate the final result, high-dime...

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 Patents(China)
IPC IPC(8): G06F16/58
CPCG06F16/5838
Inventor 唐博杨航
Owner SOUTH UNIVERSITY OF SCIENCE AND TECHNOLOGY OF CHINA
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