Processing method and system for tree structure image algorithm

A tree structure and image algorithm technology, applied in the field of image processing, can solve the problems of difficult framework agile development and high licensing costs, and achieve the effect of shortening the development cycle and reducing costs.

Inactive Publication Date: 2018-07-13
深圳市万相源科技有限公司
View PDF1 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] For programmatic software, it is necessary to call algorithm tools / functions for customized development according to actual projects. This method depends on specific projects, and it is difficult to have a unified framework for agile development.
For visualization software, the authorization fee for such software is generally relatively high. At the same time, this method is generally serial processing. For parallel processing, customized program development is still required.

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
  • Processing method and system for tree structure image algorithm
  • Processing method and system for tree structure image algorithm
  • Processing method and system for tree structure image algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0063] Example 1: Take the example of creating two root nodes with two layers of nesting for each root node:

[0064] 1) Create a new algorithm collection tree, AlgsTree;

[0065] 2) Add the first root node, Obj1, and select its associated algorithm, the contour positioning algorithm, from the algorithm library;

[0066] 3) Add the second root node, Obj2, and select its associated algorithm, the contour positioning algorithm, from the algorithm library;

[0067] 4) Select the first root node Obj1, add a child node Joint1, and select its associated algorithm, Blob analysis algorithm from the algorithm library, and anchor it under Obj1;

[0068] 5) Select the second root node Obj2, add a child node Joint2, and select its associated algorithm, Blob analysis algorithm from the algorithm library, and anchor it under Obj2;

[0069] 6) Select the child node Joint1, add a child node Cell1, and select its associated algorithm, grayscale statistical algorithm from the algorithm librar...

Embodiment 2

[0084] Embodiment 2: Take the configuration of the contour positioning tool of the root node Obj1 as an example;

[0085] 1) On the tree structure, select the node Obj1;

[0086] 2) Display the contour positioning tool parameters associated with the Obj1 node in the property box;

[0087] 3) Load the test image;

[0088] 4) In the attribute box, set the granularity to 3, click "Training Area", a rectangular training area will appear on the image, drag and drop / zoom the rectangular training area to the area of ​​interest, and then click "Training", you can Get the training outline; click "Search Area", a rectangular search area will appear on the image, drag and drop / zoom the rectangular search area to the area of ​​interest, and then click "Set"; "Search Number" is set to 1, "Search "Score" is set to 0.8; click "Search" to get the contour positioning matching results;

[0089] 5) Confirm that the parameters are correct and save them to take effect.

[0090] Further, the st...

Embodiment 3

[0103] Embodiment 3: Take the configuration of the root node Obj1 associated contour positioning tool, the child node Cir1 associated circle fitting tool, and the child node Cir2 associated circle fitting tool as an example

[0104] 1) On the tree structure, select the root node Obj1, and right-click to select the "Port Configuration" item; in the "Output Element" list of "Port Configuration", select "Coordinate Offset" as the output matching information type;

[0105] 2) On the tree structure, select the child node Cir1 under the root node Obj1, and right-click to select the "Port Configuration" item; in the "Input Element" list of "Port Configuration", select "Coordinate Offset" as the input Select the information type; in the "Output Element" list, select "Location Point"; enable the "Parallel Processing" element;

[0106] 3) On the tree structure, select the child node Cir2 under the root node Obj1, and right-click to select the "Port Configuration" item; in the "Input Ele...

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 processing method for a tree structure image algorithm. The method comprises the steps that a system establishes an image algorithm set of a tree structure; the system configures corresponding algorithm tools; the system interacts with and parallelly processes data between the algorithm tools. The processing system for the tree structure image algorithm comprises an algorithm set creating module, a tool configuration module and a data processing module. The processing method and system for the tree structure image algorithm starts from two key points of agile development and visualization operation, establishes a visual framework to solve arbitrary image algorithm combination management through general description and encapsulation of the image algorithm, and meanwhile can parallelly process problems. Compared with programming software, the method conducts agile development under the unified framework and effectively shortens the development cycle. For visualization software, the method can conduct explicitly startup and parallel processing without programming, meanwhile appropriately reduce costs, and is widely used in the image processing field.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a processing method and system for a tree structure image algorithm. Background technique [0002] In complex defect detection projects, there are often multiple detection requirements at the same time, such as target existence or non-judgment, area / grayscale judgment, size measurement, etc., and there may be multiple areas with different detection requirements at the same time, that is, in the entire image algorithm set There may be any number of image algorithm tools, and the relationship between these algorithm tools is not fixed, such as a parallel relationship or a subordination relationship, which needs to be set according to the actual detection project. [0003] In the process of building a set of image algorithms, third-party image processing software is usually used. One type is programming software, such as Halcon, opencv, etc. During the use of such software, developer...

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): G06F8/34
CPCG06F8/34
Inventor 石加彬
Owner 深圳市万相源科技有限公司
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