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

Linear feature extraction method utilizing multi-scale multi-constructing-element top-hat transformation

A technology of linear features and structural elements, used in instruments, character and pattern recognition, computer parts, etc., to achieve broad market prospects, application value, and effective extraction effects.

Inactive Publication Date: 2014-03-26
BEIHANG UNIV
View PDF7 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

(X. Bai, F. Zhou. Multi structuring element top-hat transform to detect linear features. International Conference on Signal Processing, Beijing, China, 2010, pp.877–880.)) has been well used for multi-linear In the extraction of features, however, post-processing is usually required to suppress low-contrast linear features and noisy areas

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
  • Linear feature extraction method utilizing multi-scale multi-constructing-element top-hat transformation
  • Linear feature extraction method utilizing multi-scale multi-constructing-element top-hat transformation
  • Linear feature extraction method utilizing multi-scale multi-constructing-element top-hat transformation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0061] In order to better understand the technical solutions of the present invention, the implementation manners of the present invention will be further described below in conjunction with the accompanying drawings.

[0062] Principle of the present invention and flow chart are as figure 1 Shown, the specific implementation steps of the present invention are as follows:

[0063] Step 1: Construct structural elements for extracting linear features in various directions at multiple scales

[0064] In image morphology operations, image features at different scales can be extracted by changing the size of structural elements. And the linear features of any shape in the image can be approximated by linear features in four directions of 0°, 45°, 90° and 135° in the discrete digital space. In order to more effectively extract linear features of various shapes, various lengths and various widths in the image, the present invention constructs multiple structural elements at multipl...

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 linear feature extraction method utilizing multi-scale multi-constructing-element top-hat transformation. The linear feature extraction method includes the steps of firstly, in consideration of characteristics of linear features of images, constructing multi-scale multiple constructing elements which are required by top-hat transformation and used for linear feature extraction; secondly, by means of top-hat transformation, extracting the possible linear feature in every direction under every scale respectively through the constructed constructing elements; thirdly, merging the linear features in every direction under every scale; fourthly, taking the maximum of the linear features under all scales as an extracted linear feature grey scale image; and finally obtaining the final results through follow-up processes of binaryzation, artifact reduction, thinning and small region elimination. The extracted linear features are important features for image processing related applications. Therefore, the linear feature extraction method can be widely applied to various application systems based on image processing and has broad market prospects and application value.

Description

technical field [0001] The invention relates to a linear feature extraction method using multi-scale multi-structural element top-hat selective transformation, belongs to the field of digital image processing, and mainly relates to mathematical morphology and linear feature extraction technology. It has broad application prospects in various image-based application systems. Background technique [0002] Linear features are important features of images. Feature extraction technology is an important technology for image analysis and pattern recognition related applications, such as circle or ellipse detection, corner detection, and object detection. Among them, linear feature extraction technology can usually provide more useful information for different image processing applications, such as biological engineering and industrial engineering. However, linear features in images usually have different widths, lengths, and have very low contrast. Therefore, automatic detection...

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): G06K9/46
Inventor 白相志张余周付根
Owner BEIHANG UNIV
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