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

A Graph Matching Method Based on Multi-attribute Coding and Dynamic Weights

A technology of dynamic weights and matching methods, applied in image coding, image analysis, image data processing, etc., can solve the problems of application scope, lack of robustness, limited application scope of algorithms, inability to distinguish graphics, etc., to improve stability and performance. reliability, improved robustness, guaranteed flexibility

Active Publication Date: 2022-03-22
ZHEJIANG UNIV
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although this method is efficient and stable, it is only for the calculation of the similarity of polygonal graphics, and the graphics need to be preprocessed so that the number of sides of the two graphics must be equal. Various conditions limit the scope of application of the algorithm
A method and system for constructing and matching graphics in a Chinese patent (patent application publication number: CN105335444A, authors: Liu Lu, Wang Xinghua, Lv Xiaoqing) encodes the properties of linear graphics and non-linear graphics respectively to realize complex structures, The geometric features of various types of primitives are expressed and matched, but the graphic encoding method used in this patent cannot distinguish mirror-symmetrical graphics
[0005] The above methods have certain deficiencies in the scope of application, robustness, etc., which make them somewhat stretched in the process of engineering application.

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
  • A Graph Matching Method Based on Multi-attribute Coding and Dynamic Weights
  • A Graph Matching Method Based on Multi-attribute Coding and Dynamic Weights
  • A Graph Matching Method Based on Multi-attribute Coding and Dynamic Weights

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0081] In this embodiment, according to the pattern matching method of the present invention, the figure 2 In the two graphs, the similarity distance is calculated and the corresponding edges are found.

[0082] The graphic matching process of the present invention is as figure 1 As shown, the specific implementation process is as follows:

[0083] (1) input figure 2 The two graphics of the two graphic objects to be compared are shown as figure 2 (a) and figure 2 (b), and transform them into edge attribute adjacency graph G 1 , G 2 , that is, save the geometric type and relative length information of the graph edge in the corresponding vertex set V of the adjacency graph 1 and V 2 At the same time, the adjacency information between graph edges is stored in the edge set E corresponding to the adjacency graph 1 and E 2 In Figure 2(a), the transformation result is as follows image 3 shown.

[0084] (2) According to G 1 , G 2 The information of each vertex and it...

Embodiment 2

[0123] In this embodiment, given a source graphic, the most similar graphic is retrieved from the graphic library.

[0124] source graphics such as Image 6 As shown, the graphics library such as Figure 7 shown. According to the graphic matching method of the present invention, the similarity distances of each graphic in the source graphic and the graphic library are respectively calculated, and the results are shown in Table 5.

[0125] Table 5 The similarity distance between each graph in the graph library and the source graph

[0126] graphics (1) (2) (3) (4) (5) (6) (7) (8) similar distance 0.7035 0.7324 0.7581 0.6826 0.9442 0.7190 0.7256 0.6627

[0127] Table 6 Corresponding edges between the source graph and the graph (5) in the graph library

[0128] source graphics A B C D E graphics(5) D A B C E

[0129] From the calculation results in Table 5, we can see that the best matching graph of the source g...

Embodiment 3

[0131] This embodiment is compared with the matching algorithm in the construction method, matching method and system of a Chinese patent (patent application publication number: CN105335444A, author: Liu Lu, Wang Xinghua, Lu Xiaoqing), illustrating that the matching algorithm of the present invention can Mirror symmetrical figures are distinguished. Using two matching algorithms to calculate Figure 8 The similarity distances between figure (1) and figure (2) and figure (3), in which figure (2) and figure (3) are mirror symmetric, the calculation results are shown in Table 7.

[0132] Table 7 Similarity distance calculation results of two matching algorithms

[0133] similar distance this invention other patents Graphics (1) and Graphics (2) 0.9301 0.8324 Graphics (1) and Graphics (3) 0.7422 0.8324

[0134] As can be seen from the calculation results in Table 7, due to the use of the current edge as a benchmark, the angle encoding method of de...

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 pattern matching method based on multi-attribute coding and dynamic weight. Input two graphic objects to be compared and convert them into edge attribute adjacency graphs respectively, and perform multi-attributes including basic attributes and adjacency attributes on each vertex in the edge attribute adjacency graph according to the information of vertices and edges in the edge attribute adjacency graph Encoding, using the dynamic weight method to hierarchically calculate the similarity between each two vertices in the edge attribute adjacency graph, and store them to form the vertex similarity mapping matrix. When the maximum weight matching weighted sum of the vertex similarity mapping matrix is ​​the largest, The similarity distance between two graphs and their corresponding sides can be obtained. The invention comprehensively considers the basic attributes of graphic edges and their adjacent attributes, and performs encoding and similarity calculation according to their respective characteristics, which not only improves the stability and reliability of graphic matching, but also expands its application range.

Description

technical field [0001] The invention belongs to the field of graphics and image processing, in particular to a graphics matching method based on multi-attribute coding and dynamic weight. Background technique [0002] Three-dimensional registration refers to the acquisition of accurate three-dimensional coordinates and postures of objects in three-dimensional space through computer graphics analysis, and binding and splicing of virtual objects generated by computers into real three-dimensional space according to the obtained three-dimensional coordinates, so as to achieve real environment and virtual objects. The accurate and seamless integration of AR is the basis for realizing various augmented reality systems, and it is also one of the core problems that need to be solved. [0003] The 3D registration method based on model keyframe needs to extract the geometry in the monocular image in the online stage, and match the most similar keyframe image from the image stored in t...

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): G06T7/30G06T9/20
CPCG06T7/30G06T9/20
Inventor 刘振宇王科刘达新谭建荣
Owner ZHEJIANG UNIV