Unlock instant, AI-driven research and patent intelligence for your innovation.

An Image Similarity Judgment Method Based on Improved Color Variance Algorithm

A color variance, image similarity technology, applied in the field of image processing, can solve the problems of lack of flexibility, low accuracy, not considering image rotation, etc., to achieve the effect of improving flexibility and accuracy

Active Publication Date: 2021-01-05
KUNMING UNIV OF SCI & TECH
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is to provide an image similarity judgment method based on the improved color variance algorithm in view of the limitations and deficiencies of the prior art, so as to solve the problems existing in the prior art that do not consider image rotation and flexibility when judging image similarity. Insufficient accuracy, low accuracy, etc., dedicated to improving the flexibility and accuracy of image similarity judgment using color variance algorithm

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
  • An Image Similarity Judgment Method Based on Improved Color Variance Algorithm
  • An Image Similarity Judgment Method Based on Improved Color Variance Algorithm
  • An Image Similarity Judgment Method Based on Improved Color Variance Algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0036] Embodiment 1: as Figure 1-2 As shown, an image similarity judgment method based on the improved color variance algorithm, firstly, the image is rotated in all directions through the reference image and the inspection image, and 8 images of upper, lower, left, right, upper left, lower left, upper right, and lower right are generated Cut the rotation image, then calculate the variance of the image through the color variance algorithm, calculate the variance difference value based on the color variance algorithm between the cropped and rotated images in pairs, and take the minimum value as the variance difference value between the images based on the color variance algorithm ; If the variance difference value based on the color variance algorithm is less than the similarity threshold, it is determined that the images are similar; if the variance difference value based on the color variance algorithm is greater than the similarity threshold, it is determined that the images...

Embodiment 2

[0064] Embodiment 2: On the basis of Embodiment 1, if the image A" in the step Step4.5 m , B″ n The variance difference value D based on the color variance algorithm Var (A″ m ,B″ n ), m∈[1,8], n∈[1,8] are 12 / 14 / 5 / 7 / 4 / 21 / 18 / 26 / 42 / 7 / ··· / 6 / 32 / 21 respectively, then In step Step5, the minimum value is selected by formula (4) as the variance difference value D between images A and B based on the color variance algorithm Var (A,B), whose value is D Var (A,B)=Min(D Var (A″ m ,B″ n )), m∈[1,8], n∈[1,8]=4.

Embodiment 3

[0065] Embodiment 3: On the basis of Embodiment 1, take the similarity threshold If the variance difference value D between images A and B based on the color variance algorithm in step Step5 Var (A, B)=4, then determine that image A is similar to image B; if the variance difference value D based on the color variance algorithm is between image A and B in step Step5 Var (A,B)=12, then it is determined that image A and image B are not similar.

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 an image similarity judging method based on an improved color variance algorithm, and belongs to the technical field of image processing. The present invention first rotates the image in all directions through the reference map and the survey map, and generates 8 cutting and rotating maps of up, down, left, right, upper left, lower left, upper right, and lower right, and then performs image rotation through the color variance algorithm. Variance calculation, calculate the variance difference value based on the color variance algorithm between the cropped and rotated images in pairs, and take the minimum value as the variance difference value between the images based on the color variance algorithm; the variance difference value based on the color variance algorithm is smaller than the similarity threshold, It is determined that the images are similar; if the variance value based on the color variance algorithm is greater than the similarity threshold, it is determined that the images are not similar. The invention solves the phenomena of not considering image rotation, insufficient flexibility and low accuracy in judging image similarity in the prior art, and improves the flexibility and accuracy of judging image similarity by using color variance algorithm.

Description

technical field [0001] The invention relates to an image similarity judging method based on an improved color variance algorithm, and belongs to the technical field of image processing. Background technique [0002] Image similarity judgment is a basic research in the field of image processing, which refers to the analysis and comparison of the content similarity of two or more images, and is widely used in image retrieval, object detection, photo filtering and other fields. [0003] At present, there are many methods for judging image similarity. As far as the color variance algorithm is concerned, its accuracy and efficiency are not satisfactory. One of the main reasons is that the color variance algorithm does not take into account the rotation of the image. After reversing and comparing, the result is not ideal. Contents of the invention [0004] The technical problem to be solved by the present invention is to provide an image similarity judgment method based on 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 Patents(China)
IPC IPC(8): G06K9/62G06K9/32G06K9/46
CPCG06V10/243G06V10/56G06F18/22
Inventor 彭艺尹玉梅祁俊辉
Owner KUNMING UNIV OF SCI & TECH
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com