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

Method and device for measuring image similarity

A similarity and image technology, applied in the field of data processing, can solve the problems of missing image information, low accuracy, and low accuracy of image similarity measurement, and achieve the effect of reducing the amount of calculation and improving the measurement accuracy

Inactive Publication Date: 2020-08-28
POTEVIO INFORMATION TECH CO LTD
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The existing SSIM-based measurement method can achieve results better than the PSNR measurement method, but the SSIM measurement method cannot completely solve the problems of the above-mentioned PSNR measurement method
[0005] The existing P-Hash algorithm loses most of the image information due to compressing and graying the image, so its accuracy is not high
[0006] Therefore, the existing technology has the following disadvantages as a whole: the measurement accuracy of image similarity is not high, and the calculation amount is relatively large

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
  • Method and device for measuring image similarity
  • Method and device for measuring image similarity
  • Method and device for measuring image similarity

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0060] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0061] figure 1 It is a flow chart of the method for measuring image similarity described in an embodiment of the present invention. see figure 1 , the method of the present invention is mainly divided into two steps, namely step 10 and step 20.

[0062] Step 10, extract the boundaries of the images to be compared, determine the similarity of the image boundaries, and select the images to be compared with the same boundaries or similar boundaries within a specified range.

[0063] This step 10 is equivalent to classifying the images to be compared (i.e. image pairs), and only selecting image pairs with the same boundary or similar boundaries within a specified range to perform the next step 20, while other image pairs do not need to perform the next step 20. a step 20 .

[0064] Step 20, for the selected images to be compared, usi...

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 similarity measurement method and device. The method comprises the steps that A, boundaries of to-be-compared images are extracted, the similarity between the image boundaries is determined, and the similar to-be-compared images with identical boundaries or the boundaries within a designated range are selected; and B, according to the selected to-be-compared images, structural similarity and a perceptual-hash algorithm are adopted to calculate the similarity between the images. Through the image similarity measurement method and device, measurement precision can be improved, and the calculation amount can be lowered.

Description

technical field [0001] The present application relates to the technical field of data processing, in particular to a method and device for measuring image similarity. Background technique [0002] At present, the mainstream image similarity measurement methods include similarity measurement based on color and texture features, similarity measurement method based on peak signal-to-noise ratio (PSNR), structural similarity (SSIM) measurement method, perceptual hashing algorithm (P- Hash), calculation feature point (FAST, SURF, SIFT, ORB, etc.) measurement method. [0003] Among the existing image similarity measurement methods, the PSNR-based similarity measurement method is the most common and widely used image objective evaluation method, but this method is based on the error between corresponding pixels, that is, based on the error Sensitive image quality for similarity measurement. Since the visual characteristics of the human eye are not considered, for example, the hum...

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): G06T7/00G06T7/13
CPCG06T7/0002G06T7/12G06T2207/10004
Inventor 闫继东
Owner POTEVIO INFORMATION TECH CO LTD