Similar image retrieval method

A technology similar to images and images, applied in the computer field, can solve problems such as slow calculation speed and occupied disk read and write time, and achieve the effect of reducing reading and writing pressure and increasing speed

Pending Publication Date: 2019-05-14
上海七印信息科技有限公司
View PDF4 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But, there are following problems in this retrieval method: 1, calculation speed is slow
Since each image retrieval needs to traverse the entire image feature value database and read the entire image feature value database, it takes up a lot of disk read and write time

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
  • Similar image retrieval method
  • Similar image retrieval method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] In order to make the technical means, creative features, goals and effects achieved by the present invention easy to understand, the present invention will be further described below in conjunction with specific illustrations.

[0022] see figure 2 , shown in the figure is a similar image retrieval method, including the following steps:

[0023] Step S1, acquire an image, and calculate the binary hash feature value of the image.

[0024] In step S2, the calculated binary hash feature value of the image is segmented so that the binary hash feature value is divided into several segments of hash feature values.

[0025] Step S3, judging whether the image is an image to be detected; if it is judged yes, go to step S5; if it judges no, go to step S4.

[0026] Step S4, write the binary hash feature value of the image into the constructed image feature value database for storage.

[0027] Step S5, search in the constructed image feature value database to find out all image...

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 a similar image retrieval method, which comprises the following steps of: obtaining an image to be retrieved, and calculating a binary hash characteristic value; carrying out segmentation processing on the binary hash characteristic value; carrying out retrieval in the constructed image feature value database, finding out all images containing at least one section of Hash feature value, and sorting the images into a final candidate image list; calculating a characteristic value distance between the to-be-retrieved image and each image in the candidate image list, and determining an image with the minimum characteristic value distance from the to-be-detected image in the candidate image list; judging whether the characteristic value distance between the image and theto-be-retrieved image is smaller than a preset threshold value or not; wherein the image is a similar image of the to-be-retrieved image if the image is smaller than the preset threshold value. According to the method, image retrieval is carried out in a manner of segmenting the binary hash characteristic values of the to-be-retrieved images, so that the similar image retrieval speed is greatly increased.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a similar image retrieval method. Background technique [0002] see figure 1 , the figure shows the existing similar image retrieval method, which adopts the sequential traversal method. The basic process is: 1. Extract feature values ​​from existing images in turn, and establish the extracted feature values ​​of existing images Image feature value database; 2. Extract the feature value of the image to be retrieved; 3. Compare the feature value of the image to be retrieved with the feature value of each image in the image feature value database through sequential traversal, and calculate the image to be retrieved and the eigenvalue distance between each image in the image eigenvalue database; 4. Determine the image with the smallest eigenvalue distance from the image to be retrieved in the image eigenvalue database, and determine whether the eigenvalue distance is less than a ...

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): G06F16/53G06F16/50
Inventor 缪弘
Owner 上海七印信息科技有限公司
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