Check patentability & draft patents in minutes with Patsnap Eureka AI!

An image matching method and device

A matching method and image technology, applied in the field of image processing, can solve the problems of large amount of calculation, slow calculation speed and complex feature processing process for grayscale matching.

Active Publication Date: 2019-04-26
BEIJING QIHOO TECH CO LTD
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In short, the traditional grayscale matching has a large amount of calculation and slow calculation speed, while the feature processing process of feature matching is complicated, and it is not convenient to match images

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 matching method and device
  • An image matching method and device
  • An image matching method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0081] refer to figure 1 , which shows a schematic flow chart of an image matching method of the present invention, which may specifically include:

[0082] Step 110, for the reference image and the image to be matched, obtain the pixel values ​​of the respective pixel points of the respective images;

[0083] In practical applications, an image that can be displayed on various terminals is composed of pixels, and each pixel has a pixel value, such as the REG value in a computer system, which is composed of red R, Green G and blue B are composed of three color channels. Each value of R, G, and B can take any value from 0 to 255. When all three colors are 255, it is white, and when all three colors are 0, it is black. Therefore, there are totally 255*255*255=16581375 kinds of values ​​for the pixel value.

[0084] Then, for an image, the present invention can obtain the REG value of its pixel, for example, the REG value of a certain pixel is (0, 100, 100).

[0085] In this e...

Embodiment 2

[0164] In this embodiment, the present invention is introduced by acquiring directions from behaviors of pixels in an image. Of course, the principle is similar to the row for the case where the column of pixels is the acquisition direction. In this embodiment, Chinese characters are used as character identifiers.

[0165] refer to figure 2 , which shows a schematic flow chart of an image matching method of the present invention, which may specifically include:

[0166] Step 210, for each image in the reference image and the image to be matched, obtain the pixel values ​​of each pixel point one by one in a row direction from the upper left corner of the image.

[0167] In the embodiment of the present invention, when the system is initialized, the non-repetitive Chinese character list strCopor can be loaded in advance, and an initial mark dictionary dict is loaded, that is, the mark dictionary in the initial state does not record any "pixel value-Chinese character" pair.

...

Embodiment 3

[0202] refer to image 3 , which shows a schematic structural diagram of an image matching device of the present invention, which may specifically include:

[0203] The pixel value acquisition module 310 is adapted to acquire the pixel values ​​of the respective pixel points of the respective images for the reference image and the image to be matched;

[0204] The character marking module 320 is adapted to use a unique character identification for the same pixel value in each pixel point, and mark the pixel value according to the position of the pixel point, so as to obtain the reference string sequence corresponding to the reference image respectively and the string sequence to be matched corresponding to the image to be matched;

[0205] The matching module 330 is adapted to match the character strings in the to-be-matched character string sequence with the character strings in the reference character string sequence, so as to determine whether the to-be-matched image match...

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 matching method and device and relates to the technical field of image processing. The method comprises the following steps: for a reference image and an image to be matched, respectively obtaining the pixel value of each pixel point of each image; for the same kind of pixel value in each pixel point, using the unique character identification to mark the pixel value according to the position of the pixel point, and thus respectively obtaining a reference character string sequence corresponding to the reference image and a sequence of character strings to be matched corresponding to the image to be matched; matching the character strings in the sequence of character strings to be matched with the character strings in the reference character string sequence so as to determine whether the image to be matched is matched with the reference image or not. The method solves the problems of large calculated amount and low calculating speed of gray scale matching, avoids the complicated characteristic processing process of characteristic matching, and obtains the benefit that the method can quickly carry out image matching but does not adopt an additional characteristic extraction way and does not directly process gray scale information.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to an image matching method and device. Background technique [0002] Image matching refers to the method of finding the same image target through the similarity and consistency analysis of the corresponding relationship between image content, features, structure, relationship, texture and gray level. The current image matching can be mainly divided into grayscale-based matching and feature-based matching. The basic idea of ​​grayscale matching is: regard the image as a two-dimensional signal from a statistical point of view, use the statistical correlation method to find the correlation match between the signals, and use the correlation function of two two-dimensional signals to evaluate their similarity to determine Same-name point; gray-scale matching determines the correspondence between two images by using some similarity measure, such as correlation function, covaria...

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): G06K9/62
Inventor 洪丽娜
Owner BEIJING QIHOO TECH CO LTD
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