Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Quick identification method for binary image connected domain marker

A connected domain labeling and binary image technology, applied in the field of image processing, can solve the problems of unsuitable parallelization, low efficiency, and lack of real-time processing of large images, and achieve the effect of improving overall performance, improving scanning efficiency, and simple method.

Inactive Publication Date: 2015-04-08
LIUZHOU VOCATIONAL & TECHN COLLEGE
View PDF3 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Existing methods have the defects of low efficiency, not suitable for parallelization, and lack of real-time processing of large 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
  • Quick identification method for binary image connected domain marker
  • Quick identification method for binary image connected domain marker
  • Quick identification method for binary image connected domain marker

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0038] Such as figure 1 As shown, a binary image connected domain label fast recognition method, including the following steps:

[0039] S1. Initialization of CPU and GPU:

[0040] The server environment is used to establish a virtual graphics workstation cluster. The virtual graphics workstation is logically combined to form a dynamic virtual machine. The server environment includes a server cluster and a main control server, that is, the server environment includes multiple CUDA-based GPU graphics cards installed on the server cluster. The GPU graphics cards are connected through the SLI interface (Scalable Link Interface, upgradeable connection interface), and the block size of the CUDA architecture platform is 256 or 512; the server cluster is used as a computing node, and the main control server is responsible for scheduling and controlling all tasks, and is responsible for Manage the computing of each node on the cluster and integrate storage resources;

[0041] S2. ...

Embodiment 2

[0054] The difference from Embodiment 1 is that the server environment includes a server computer and a master server.

[0055] S1. The initialization of CPU and GPU is specifically:

[0056] Use the server environment to establish a cluster of virtual graphics workstations. The virtual graphics workstations are logically combined to form a dynamic virtual machine. The server environment includes a server computer and a master server, that is, the server environment includes multiple CUDA-based GPU graphics cards installed on the server computer. Each GPU graphics card is connected through the SLI interface, and the block size of the CUDA architecture platform is 256 or 512; the server computer is used as a computing node, and the main control server is responsible for scheduling and controlling all tasks, and is responsible for managing the calculation of each node and storage resource integration;

[0057] The technical solution of the present invention is used in image re...

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 quick identification method for a binary image connected domain marker. The quick identification method comprises the steps: initializing a CPU (central processing unit) and a GPU (graphics processing unit); scanning an image; storing scanning results in a magnetic disk of a server environment; combining the scanning results; judging whether iterative scanning exists, and storing a result to end the operation. The quick identification method has the advantages of capability of improving efficiency, suitability for parallelization and real-time processing of large images.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a method for quickly identifying connected domain markers in a binary image. Background technique [0002] Currently, a binary image refers to an image in which each pixel is either black or white, and its gray value has no intermediate transition. The advantage is that it takes up less space. The disadvantage is that when representing images of people and landscapes, binary images can only describe their outlines and cannot describe details. The existing connected domain labeling methods include: connected point-by-point scanning method, this method needs to deal with a large number of repeated labels, the logic is complex, and the efficiency is low. [0003] Seed filling method, which is more efficient, but not suitable for parallelization. [0004] The above two types of methods are serial designs, and do not have the conditions for real-time processing of large images. [...

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): G06F9/38
Inventor 余剑王慧韦小波陆晓希杨洁巫江
Owner LIUZHOU VOCATIONAL & TECHN COLLEGE
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products