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

Feature Extraction Method Based on Image Neighborhood Structural Tensor Equation

A technology of structure tensor and feature extraction, applied in the field of algorithms, can solve problems such as difficult positioning and recognition edge blurring, and achieve the effect of accurate boundaries and simple methods

Active Publication Date: 2020-04-10
SHANGHAI SMARTEE DENTI TECH CO LTD
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In the prior art, Data Matrix is ​​mostly used in printing, engraving, photolithography, corrosion, stamping and other methods. The recognition method of the two-dimensional code generated by these methods is relatively simple because the recognition degree of its edge is high, but the method of 3D printing is adopted. , to directly generate a two-dimensional code, its recognition edge is fuzzy, and it is difficult to achieve positioning. Therefore, it is of great significance to study a method that can perform regional positioning on the two-dimensional code generated by the 3D printing method.

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
  • Feature Extraction Method Based on Image Neighborhood Structural Tensor Equation
  • Feature Extraction Method Based on Image Neighborhood Structural Tensor Equation
  • Feature Extraction Method Based on Image Neighborhood Structural Tensor Equation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0047] Embodiment 1 A feature extraction method based on image neighborhood structure tensor

[0048] A feature extraction method based on image neighborhood structure tensor, which is performed in the following steps:

[0049] 1) Determine the lower boundary of the QR code;

[0050] a) Calculate the image centroid;

[0051]For a two-dimensional discrete digital image, its order geometric moment is defined as:

[0052] ; Among them, p, q=0,1,2..., M, N are the width and height of the image;

[0053] The formula for calculating the center of mass is:

[0054] ; where x 0 is the abscissa of the centroid, y 0 is the vertical coordinate of the centroid;

[0055] b) Intercept the area of ​​pixels around the centroid, and calculate its grayscale histogram curve according to the rows of the image matrix;

[0056] c) After obtaining the histogram curve, find the line where the global minimum value of the curve is located as the estimated area of ​​the lower boundary of the two-...

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 feature extraction method based on an image neighborhood structure tensor equation. The method comprises the following steps: 1) determining a lower boundary of a two-dimensional code; 2) performing region extraction by use of a region growth method; 3) computing a feature value based on the structure tensor; and 4) fitting other three obtained discrete boundaries by use of the least square method to obtain a final standard datamatix two-dimensional code region. The neighborhood boundary of the two-dimensional code is determined through the region growth method and the feature computation of the structure tensor by use of the method disclosed by the invention; compared with the method for determining each boundary region, the method disclosed by the invention is simpler, and the determined boundary is more accurate; and the method is suitable for the extraction of the two-dimensional code region.

Description

technical field [0001] The invention belongs to the field of algorithms, and relates to a region feature extraction method, in particular to a feature extraction method based on an image neighborhood structure tensor equation. Background technique [0002] Data Matrix is ​​a QR code widely used in international manufacturing. Data Matrix is ​​a member of the two-dimensional code, invented by the American International Data Corporation in 1989, and is widely used for anti-counterfeiting and overall identification of commodities. It is a code that can be directly marked on a solid surface. The code can be automatically read by the corresponding scanning device like an ordinary barcode, and is very popular in the manufacturing industry. At present, Data Matrix is ​​widely used in product identification, anti-counterfeiting, quality tracking, automatic storage, logistics management and control and other systems. Data Matrix adopts complex error correction code technology, whic...

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 Patents(China)
IPC IPC(8): G06K7/14
CPCG06K7/1417
Inventor 查凯王龙姚峻峰
Owner SHANGHAI SMARTEE DENTI 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