Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Method for automatically training shape matching model

A matching model and automatic technology, applied in character and pattern recognition, instrument, calculation, etc., can solve the problems of high usage threshold and many parameters

Active Publication Date: 2021-09-10
ROKAE SHANDONG INTELLIGENT TECH CO LTD
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

It can be seen that this method needs to set a lot of parameters, requires certain professional knowledge, and has a high threshold for use

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 automatically training shape matching model
  • Method for automatically training shape matching model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0049] Embodiments of the present invention are described in detail below, examples of which are shown in the drawings, wherein the same or similar reference numerals designate the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the figures are exemplary and are intended to explain the present invention and should not be construed as limiting the present invention.

[0050] The invention proposes a method for automatically determining the training model required for shape matching, which simplifies the setting of parameters and realizes the automation of model training.

[0051] It should be noted that the implementation of the present invention requires the following hardware modules:

[0052] (1) Camera (including lens). The camera cooperates with the lens to collect images, and the camera can communicate with the processor through various communication methods.

[0053] (2) Processor. T...

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 provides a method for automatically training a shape matching model. The method comprises the following steps: S1, acquiring an image without a target; S2, acquiring an image containing a target; S3, acquiring a plurality of difference regions of the two images acquired in the step S1 and the step S2; S4, calculating the minimum bounding rectangle or ellipse of each area and the angle formed by the long axis of the minimum bounding rectangle or ellipse and the x axis of the image; S5, extracting edge points for all the difference regions, and calculating gray-scale-based gradient information of each edge point; S6, randomly selecting edge points in a difference region to train an initial model; S7, modifying the model through edge points in other areas to obtain a model suitable for all targets; and S8, searching targets in the image acquired in the step S2 by using the modified model, if all targets cannot be found or the maximum number of iterations is reached, returning to the step S5, and taking the model obtained by the last iteration as a final model.

Description

technical field [0001] The invention relates to the technical field of image positioning processing, in particular to a method for automatically training a shape matching model. Background technique [0002] Template matching is a technique of searching an image for another image (called a template image), and is widely used to locate objects in an image. The basic idea is: first, train the model according to the characteristics of the template image, then use the model information to search the template image in the new image, and finally get the position of the target in the new image. [0003] In current machine vision software, template matching is a commonly used function, and the first step is to obtain a template image and then train the model. The process of training the model is: 1. Place the target to be located in the field of view and obtain an image containing the target; 2. Set the ROI containing the target in the image and use the part of the ROI as a templat...

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): G06K9/62
CPCG06F18/214
Inventor 庹华袁顺宁张彪李亚楠韩峰涛耿旭达任赜宇张雷
Owner ROKAE SHANDONG INTELLIGENT TECH CO LTD
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
Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com