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

Index structuring method for fast searching mass picture based on content

A construction method and picture technology, applied in special data processing applications, instruments, calculations, etc., can solve problems such as non-disclosure, and achieve the effects of improving robustness, reducing storage capacity, and increasing computing speed

Inactive Publication Date: 2005-10-26
NEW FOUNDER HLDG DEV LLC +1
View PDF0 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the actual use environment, abnormal terminations such as system power failures occasionally occur. In this case, a robust and practical system should continue to work normally after the system is restarted, and there should be no problems such as the index system being destroyed. , there is no public technical means in this regard

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
  • Index structuring method for fast searching mass picture based on content

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0060] The specific embodiment of the present invention will be further described below in conjunction with the accompanying drawings.

[0061] Such as figure 1 As shown, an index construction method for content-based fast retrieval of massive images includes the following steps:

[0062] 1) Read image file: read in an image file that has not been added to the index library from the image library;

[0063] Analyze image features: extract image features, which include color, texture, layout, and other information;

[0064] 2) Non-linear quantization of image features: according to the distribution information of image feature values, the image feature analysis results (ie, a set of real numbers) obtained in step 2 are quantized into integers between 1 and 255 using a nonlinear method, And expressed in 1 computer byte (Byte);

[0065] 3) Check whether the index structure tree is in the memory, if not in the memory, then read from the disk file, if there is no relevant index f...

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 relates to a method for constructing the index for content-based heavy-capacity picture fast search, belonging to an intelligent information processing technique. In the existing techniques, the searching efficiency is low and the system robustness is not strong enough. For this, on the basis of balancing the index structure of multipath search trees, the invention introduces a clustering regulation mechanism and advances a minimum complete subtree updating policy and a nonlinear property quantization algorithm. The invention will largely enhance the performance of the index structure, reduces search response time and enhances the system robustness, and has an important application value in the content-based heavy-capacity picture fast searching system.

Description

technical field [0001] The invention belongs to intelligent information processing technology, and specifically relates to an index construction method for content-based rapid retrieval of massive pictures. Background technique [0002] The content-based image retrieval method can avoid manual labeling, overcome the subjectivity and information loss of describing images with words, and thus become the main technical means of image retrieval at present. With the massive increase of digital images, the image library becomes larger and larger. When using the "sequential search" method for retrieval, it is necessary to compare the query sample image with each image in the image library, which is difficult to meet the requirements of practical applications. Quick response to requests. For this reason, people adopt the index structure of similar search to improve the speed of retrieval. At present, the main similarity search index structures mainly include K-D-B tree, R-tree, SS...

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
IPC IPC(8): G06F17/30
Inventor 杨建武吴於茜陈晓鸥刘灿
Owner NEW FOUNDER HLDG DEV LLC
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