Method for multi-subtree-based distributed image training and searching

A training method and multi-subtree technology, applied in character and pattern recognition, special data processing applications, instruments, etc., can solve problems such as long time

Active Publication Date: 2013-10-02
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF4 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to obtain better matching accuracy in the large-scale image training set, the existing vocabulary tree image processing technology including the above-mentioned public documents needs to generate a huge vocabulary tree, which is a big burden on the hardware memory overhead of the aforementioned computing nodes. Test, it takes a long time to generate a huge vocabulary tree at the same time

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 for multi-subtree-based distributed image training and searching

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] The specific embodiment of the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0026] figure 1 It shows a schematic diagram of a specific embodiment of the present invention. Before the training is finished, it is the training process of the task subtree, and after the training is finished, it is the image retrieval process. The hardware for realizing the present invention includes a plurality of interconnected servers, one of which serves as a management node, and the remaining servers serve as computing nodes.

[0027] The multi-subtree-based distributed image training method of the present invention comprises the following steps:

[0028] Step 1. The computing node selects k initial clustering centers, executes the first-level clustering, obtains k new clustering centers, and sends the information of the clustering centers to the management center first, and the management node clusters Central point info...

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

A method for multi-subtree-based distributed image training and searching comprises the following steps: step 1, selecting initial cluster central points and clustering by computational nodes, and distributing the clustered new cluster central points to each computational nodes; step 2, training task subtrees by each computational node, and taking a cluster central point as a task subtree growing point. The method for multi-subtree-based distributed image training and searching further comprises step 3, extracting feature points from the image to be searched, and transmitting the feature points to corresponding computational nodes according to cluster central point affiliation; step 4, utilizing task subtree to process and transmitting the results to management nodes by the computational nodes, and summarizing the computational results of computational nodes to acquire image searching results by the management nodes. The method can divide the training task of one vocabulary tree into the training tasks of a plurality of subtrees, enable a plurality of computational nodes to process in parallel so as to accommodate larger image training set for strong expansibility, meanwhile reduce the time cost for process of image training and searching.

Description

technical field [0001] The invention belongs to the field of computer software and relates to image processing technology, in particular to a multi-subtree-based distributed image training and retrieval method. Background technique [0002] Distributed computing is a data processing process that uses multiple computing nodes to divide tasks that require huge computing power into multiple small tasks and distribute them to multiple computing nodes, let them process in parallel, and then aggregate the results. The so-called computing nodes may be multiple computers, servers, or multiple software programs running simultaneously on one computer. [0003] Image retrieval is to compare the image to be recognized with a comparison image library containing multiple comparison images, that is, each comparison image in the training set, and find the comparison image with the highest similarity between the training set and the image to be recognized. [0004] Due to the existence of b...

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): G06K9/62G06F17/30
Inventor 段翰聪李林聂晓文张建邹浩彭玉炳
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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