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

Method for automatically extracting relative numerical coordinates of picture curve

An automatic extraction and curve technology, applied in image data processing, image analysis, 2D image generation, etc., can solve problems such as the inability to directly obtain image numerical information.

Pending Publication Date: 2021-09-14
BEIJING INST OF OPTO-ELECTRONIC TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

People can easily obtain visual image data, but in most cases, they cannot directly obtain the numerical information in the image

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 extracting relative numerical coordinates of picture curve
  • Method for automatically extracting relative numerical coordinates of picture curve
  • Method for automatically extracting relative numerical coordinates of picture curve

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] The following is attached Figure 1-13 The present invention is described in further detail.

[0035] 1. Build a dataset

[0036] Because two neural networks are involved, two independent data sets need to be established respectively. In order to improve the construction efficiency of the dataset, a construction idea based on artificial data is proposed, as follows.

[0037] a, Generate the dataset of neural network model 1

[0038] Randomly generate a series of curve data points, as shown in Table 1,

[0039] Table 1

[0040]

[0041] Draw the data points in Table 1 into a graph, such as Figure 1-Figure 4 as shown,

[0042] For example Figure 1-Figure 4 The curve picture shown is in accordance with the Figure 5-Figure 8 Mark the precise position of the curve range in a way, combined with such as Figure 1-Figure 4 The curve picture shown and as Figure 5-Figure 8 The position of the labeled frame of the curve shown is the labeled data set built into the...

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 relates to a method for automatically extracting relative numerical coordinates of a picture curve, which comprises the following steps of: randomly generating a series of curve data points, drawing the curve data points into a curve graph, then labeling a curve range position to obtain a curve labeling box position, and constructing a data set of a first model by combining the curve graph and the labeling box position; taking out the image in the marking frame, and shrinking the image to a certain size to obtain a standardized picture; setting the number of curve data points corresponding to the standardized picture to be the same as the number of output values of the second model, standardizing the numerical values of all the data points, and obtaining label values needed by the second model; constructing a data set of the second model in combination with the standardized picture and a label value required by the second model; training a curve range detection model based on the data set of the first model; training a curve relative coordinate prediction model based on the data set of the second model; and inputting a to-be-detected picture into the first model and the second model to obtain a predicted value of the relative coordinates of the original curve.

Description

technical field [0001] The invention relates to a method for digitizing image information, in particular to a method for automatically extracting relative numerical coordinates of picture curves. Background technique [0002] Data graphs are an important way to communicate scientific theories and technologies, and free access to data can accelerate the promotion and application of new technologies. People can easily obtain visualized image data, but in most cases, they cannot directly obtain the numerical information in the image. To solve this problem, some semi-automatic methods have been proposed. For example, when the color of the curve in the picture is different from the background, the color of the curve can be artificially selected for curve pixel extraction, or when the curve in the picture is connected by multiple polylines When forming, the curve is automatically regenerated by artificially selecting nodes on the curve. In addition to the need for human particip...

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): G06T7/70G06T11/20G06N3/04
CPCG06T7/70G06T11/203G06N3/045
Inventor 高峰利李绍林锥王怀喜
Owner BEIJING INST OF OPTO-ELECTRONIC TECH
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

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