Picture similarity calculation method

A similarity calculation and similarity technology, applied in computing, computer parts, instruments, etc., can solve the problems of inaccurate picture similarity results and high picture similarity, reducing calculation speed, strong robustness, and improving accuracy. rate effect

Active Publication Date: 2017-05-10
SOUTH CHINA UNIV OF TECH
View PDF4 Cites 36 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to aim at the above-mentioned deficiencies in the prior art, provide a kind of picture similarity calculation method, this method combines the hash method based on DCT and the hash method based on radial projection to calculate the similarity of pictures, solves the problem of similarity In the field of image search and video key frame similarity calculation, the single pHash method can calculate the similarity of different content images is very high, and the image similarity results are not accurate enough.

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
  • Picture similarity calculation method
  • Picture similarity calculation method
  • Picture similarity calculation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0044] This embodiment provides a method for calculating image similarity, such as figure 1 Shown, be the concrete flowchart of this method, this method comprises the following steps:

[0045] 1) Use the DCT-based hash method to calculate the hash values ​​h_a and h_b of the two pictures to be compared respectively;

[0046] In this step, the DCT-based hash method uses discrete cosine transform to extract the low-frequency components of the picture, first converts the picture into a grayscale image of a standard size, then performs DCT transformation on the grayscale image, and then extracts 64 from the coefficient matrix. The hash value of the bit is used as a fingerprint, and the DCT-based hash method flow chart is as follows figure 2 shown, including the following specific steps:

[0047] 1. Reduce the image to 32*32 and grayscale to obtain a grayscale image to reduce the amount of calculation;

[0048] Two, the DCT transformation of the grayscale image obtained in the ...

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 picture similarity calculation method, comprising the steps of: (1) calculating hash values of two pictures to be compared by using a hash method based on DCT (Discrete Cosine Transformation); (2) calculating the Hamming distance dis-h between the two hash values; (3) if the Hamming distance is not in a set range, directly calculating the similarity of the two pictures via a formula; (4) if the Hamming distance is in the set range, calculating a hash value by using a hash method based on radial projection; and (5) calculating a Pearson's correlation coefficient of the hash value obtained last step, and calculating the similarity of the two pictures in combination with the Hamming distance obtained in step 2. The method has certain robustness for image rotation, avoids the influence caused by gamma correction or color histogram adjustment, and improves the accuracy of picture similarity results.

Description

technical field [0001] The invention relates to the field of computer algorithms, in particular to a picture similarity calculation method, which can be applied to similar picture retrieval and video key frame similarity calculation. Background technique [0002] At present, image similarity calculation is widely used in similar image search, video similarity calculation and other fields. As one of the main methods for image similarity calculation, the pHash method mainly includes DCT-based hash method and radial projection-based hash method. The two methods express images from different angles, and finally calculate the similarity by calculating the Hamming distance of the hash values ​​of the two images. [0003] Method 1 The idea of ​​the DCT-based hash method is to use discrete cosine transform (DCT) to extract the low-frequency components of the picture, first convert the picture into a grayscale image of standard size, then perform DCT transformation on the grayscale i...

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): G06K9/62
CPCG06F18/22
Inventor 胡丹李楚怡余卫宇
Owner SOUTH CHINA UNIV OF TECH
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