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

Structure-based dependency graph node similarity concurrent computation method

A parallel computing and similarity technology, applied in computing, image data processing, image data processing, etc., can solve the problems of increased computing time for similarity diffusion, increased computational complexity, and failure to meet needs, so as to improve accuracy and reduce complexity The effect of degree and computation time

Active Publication Date: 2013-06-26
深圳市康鸿泰科技有限公司
View PDF2 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] As the scale of the graph increases, the calculation time of similarity diffusion will increase greatly, increasing the complexity of calculation, and the complexity can even reach O(kn 4 ), which cannot meet the needs of practical applications

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
  • Structure-based dependency graph node similarity concurrent computation method
  • Structure-based dependency graph node similarity concurrent computation method
  • Structure-based dependency graph node similarity concurrent computation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0044] 101: The CPU end reads multiple story texts as the host end, establishes a graph model, and obtains the first adjacency matrix W of the graph;

[0045] The nodes in the graph represent the words in the story, and the edges between the nodes represent the similarity between the nodes. According to the first similarity measurement rule, the edge relationship between the words in the story and the words between the stories is established in the graph model, and the obtained The first adjacency matrix W of the graph.

[0046] Wherein, the first similarity measurement rule is set according to the needs in practical applications, for example: the similarity measurement between words in the story consists of the frequency of occurrence of word A, the frequency of occurrence of word B, and the co-occurrence of word A and word B and The number of times the distance between two words is less than the preset value is jointly determined; the similarity measure of words between stor...

Embodiment 2

[0060] 201: The CPU side acts as the host side to input multiple images, establish a graph model, and obtain the second adjacency matrix W and transition matrix T of the graph;

[0061] The nodes in the graph represent the superpixels in the image, and the edges between nodes represent the similarity between nodes, and according to the second similarity measurement rule, the superpixels in an image and the superpixels in different images are compared Establish the edge relationship in the graph model, and finally calculate the second adjacency matrix W, and calculate the transfer matrix T from the second adjacency matrix W, and read in the algorithm parameter constant attenuation factor C and error err.

[0062] Among them, the second similarity measurement rule is set according to the needs in practical applications, for example: calculate and obtain a region descriptor for each superpixel, calculate the similarity between two pairs of superpixels in the image through the regi...

Embodiment 3

[0083] When the scale of the graph is large and sparse, in order to increase the speed of calculating the second adjacency matrix, the method may also calculate the second adjacency matrix through step 302 .

[0084] 301: The CPU side acts as the host side to input multiple images, establish a graph model for them, obtain the second adjacency matrix W and transition matrix T of the graph, and store the transition matrix T in a CRS (Compressed Row Storage) structure as sparse matrix;

[0085] This storage form uses contiguous memory locations to store the following vectors: the val row array stores the non-zero matrix elements in row-major order, the col array stores the column index of each element in the val array, and the rowptr vector stores the index of the beginning row in the val array Element ordinal.

[0086] The nodes in the graph represent the superpixels in the image, and the edges between nodes represent the similarity between nodes, and according to the second si...

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 structure-based dependency graph node similarity concurrent computation method. The method comprises the following steps of: a CPU (central processing unit) end is taken as a host machine end, reading a plurality of story texts or graphics, and building a graph model to obtain adjacent matrixes of the graphics; a GPU (graphics processing unit) end is taken as an equipment end, receiving the adjacent matrixes output by the CPU end, and computing the adjacent matrixes by the GPU end; and obtaining the adjacent matrixes by the GPU end, and transmitting to the CPU end. According to the method, after the concurrent method is used, the similarity computation speed can be greatly accelerated, the higher computation precision can be guaranteed, and the efficiency and precision requirements of the computation and the application of a mass of medias can be met; and the experiment result shows that on the premise of similar precision, the acceleration algorithm provided by the method obtains the speed-up ratio which is averagely more than 100 times as high as the speed-up ratio obtained by the existing algorithm.

Description

technical field [0001] The invention relates to the field of media computing, in particular to a structure-based parallel computing method for graph node similarity. Background technique [0002] At present, in the field of media computing, when solving problems such as image segmentation, content retrieval and matching, the corresponding results are obtained based on the similarity diffusion between nodes by constructing a graph model. To put it simply, graph node similarity calculation is a means to evaluate the structural similarity of nodes (such as superpixels) in a graph. [0003] In the prior art, descriptors between nodes are usually used to measure the similarity between two nodes, and similarity diffusion is performed based on the similarity relationship and adjacency relationship between node neighbors. [0004] In the process of realizing the present invention, the inventor finds that at least the following disadvantages and deficiencies exist in the prior art: ...

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): G06T1/00G06T1/20
Inventor 冯伟万亮谭志羽鲁志超江健民
Owner 深圳市康鸿泰科技有限公司
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