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

Image deduplication method and device based on feature point matching

A feature point matching and image feature point technology, applied in the field of image processing, can solve problems such as large computational complexity, save storage space, reduce computational complexity, and improve computational complexity.

Pending Publication Date: 2020-05-29
NARI INFORMATION & COMM TECH
View PDF2 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to solve the deficiencies in the prior art, the present invention provides an image deduplication method and device based on feature point matching, which solves the problem of extremely high computational complexity caused by pairwise comparison of feature points

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 deduplication method and device based on feature point matching
  • Image deduplication method and device based on feature point matching
  • Image deduplication method and device based on feature point matching

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0036] An image deduplication method based on image feature point matching, comprising steps:

[0037] Step 1, extracting the first-order color moment and second-order color moment features of each image in the redundant image set to obtain a color feature vector;

[0038] Step 2, use a clustering algorithm to cluster the color features, and cluster the images into K classes;

[0039] Step 3, extract SURF features in all images;

[0040] Step 4: Perform SURF feature point matching on the images in each class. If the number of matching points is greater than the set matching threshold, it is judged as the same image, and redundant images are deleted; repeat steps 2 to 4 several times to obtain the deduplicated image. image dataset.

[0041] Further, the characteristics of the first-order color moment and the second-order color moment are:

[0042]

[0043]

[0044] Among them, μ i is the first-order color moment of the i-th image, p ij is the gray value of the jth pi...

Embodiment 2

[0048] An image deduplication device based on image feature point matching, comprising:

[0049] The color feature extraction module is used to extract the first-order color moment and second-order color moment features of each image in the redundant image set to obtain a color feature vector;

[0050] Clustering module, for adopting clustering algorithm to carry out clustering to color characteristic, image is clustered into K classes;

[0051] SURF feature extraction module for extracting SURF features in all images;

[0052]The SURF feature point matching module is used to perform SURF feature point matching on images in each class. If the number of matching points is greater than the set matching threshold, it is judged to be the same image, and redundant images are deleted; the clustering and matching process is repeated several times , to get the deduplicated image data set.

[0053] Further, the characteristics of the first-order color moment and the second-order colo...

Embodiment 3

[0060] Such as figure 1 As shown, an image deduplication method based on feature point matching, including steps:

[0061] Step 1, extracting the first-order color moment and second-order color moment features of each image in the redundant image set to obtain a color feature vector;

[0062] The first-order moment and second-order moment are defined as formulas (1) and (2):

[0063]

[0064]

[0065] Among them, μ i is the first-order color moment of the i-th image, p ij is the gray value of the jth pixel of the i-th image, N is the total number of pixels of the i-th image, σ i is the second-order color moment of the i-th image, j is the serial number of the pixel, j=1,2,...,N.

[0066] Extract image color features: Calculate the first-order color moment and second-order color moment of the image, that is, calculate the mean and variance of the pixel gray value of each image. The image is composed of RGB color space, so the extracted first-order color moments and s...

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 deduplication method and device based on feature point matching, and the method comprises the steps: extracting the first-order color moment and second-order color moment features of each image in a redundant image set to obtain a color feature vector; clustering the color features by adopting a clustering algorithm, and clustering the images into K classes; extracting SURF features in all the images; carrying out SURF feature point matching on the images in each class, if the number of matching points is larger than a set matching threshold value, judging thatthe images are the same, and deleting redundant images; repeating for multiple times to obtain a deduplicated image data set. According to the method, through pre-classification, the defect of greatcalculation complexity caused by pairwise comparison required by feature point matching is improved.

Description

technical field [0001] The invention proposes an image deduplication method and device based on feature point matching, and relates to the technical field of image processing. Background technique [0002] With the advent of the information age and the rapid development of camera, mobile phone and other photo tools, the image data on the network has exploded. However, there are a lot of repeated or similar redundant images in these images, which makes us need to consume a lot of resources to store and manage them. At the same time, a large number of redundant images will affect our further processing and utilization of images, so it is necessary to take measures to deduplicate redundant images. It is unrealistic to deduplicate images with a huge amount of data by manual screening, so there is an urgent need for a method that can intelligently determine whether images are repeated and delete redundant images. [0003] Among the image features, there are many features that c...

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): G06K9/62G06F16/50G06F16/55
CPCG06F16/50G06F16/55G06F18/22G06F18/23213
Inventor 罗旺彭启伟郝小龙张佩夏源吴超
Owner NARI INFORMATION & COMM TECH
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