Image searching method

An image retrieval and image technology, applied in special data processing applications, instruments, electrical digital data processing, etc., can solve problems such as heavy burden and time overhead, complexity of image feature description, abnormal cumbersomeness, etc.

Inactive Publication Date: 2010-10-13
南京来坞信息科技有限公司
View PDF3 Cites 66 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

There are two obvious deficiencies in this technique: First, the complexity of image feature description makes feature description for a large number of images an extremely tedious task
This method usually brings a large burden and time overhead to the user

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 searching method
  • Image searching method
  • Image searching method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0087] figure 2 Taking three different images of the same scene as an example, the process of supplementing the initial feature point set of each image in the image database and generating the same point set is given. Step 20 is the initial action. Step 21 selects the point set C with the most feature points as the matching reference feature point set. Step 22 For each feature point in the feature point set A, seek its nearest neighbor matching based on the descriptor vector Euler distance in the reference feature point set C to obtain the initial matching set, and use the ratio threshold of the nearest neighbor and the second closest neighbor (0.8 ) to filter out matching relationships greater than the threshold. In step 23, for all the coordinate pairs of the matching point set obtained in step 22, use the RANSAC algorithm to robustly determine the exact coordinate matching subset and the linear mapping relationship matrix corresponding to the transformation. The executi...

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 searching method, which comprises a training part and a searching part, wherein the training part comprises the following steps of: the extraction of characteristic points, the supplementation of the characteristic points and the determination of matching relationships, the generation of similar point set, the clustering of the characteristic point sets and the generation of characteristic vectors of each image in an image database; and the searching part comprises the following steps of: extracting the characteristic points of a picture to be retrieved and generating the characteristic point sets; calculating distances between each characteristic point descriptor vector and corresponding cluster centers, and determining a cluster where a current characteristic point belongs by using a smallest distance; calculating the frequency ni of each cluster where the characteristic points of the picture to be retrieved belong; based on the frequency ni of the clusters where the characteristic points of the picture to be retrieved belong, and the probability logarithm wi of each cluster, generating and unitizing the characteristic vector; and calculating Euler distances between the characteristic vector of the picture to be retrieved and the characteristic vectors of each image in a picture library, and selecting the image output with the smallest distance as a searching result.

Description

technical field [0001] The invention relates to an image retrieval method, in particular to an unguided image retrieval method based on feature point extraction in an image database. Background technique [0002] With the rapid development of computer technology and multimedia technology, people have more and more ways to obtain digital images, and their ability to obtain digital images is becoming stronger and stronger. The acquisition and storage of a large number of pictures makes effective management of the picture library a difficult problem. Among them, given the picture to be retrieved, how to quickly and accurately find the picture that the user wants from the image library is one of the most basic but most commonly used problems. An effective means to solve this problem is image retrieval technology. Commonly used image retrieval techniques can be mainly divided into two types: text-based and content-based. Among them, the text-based image retrieval technology us...

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
Inventor 郭延文汪粼波
Owner 南京来坞信息科技有限公司
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