Strong noise image characteristic points automatic extraction method

An image feature point and automatic extraction technology, which is applied in the direction of instruments, character and pattern recognition, computer components, etc., can solve problems such as poor stability, low precision, and large noise interference, and achieve the effect of stable algorithm and high automatic extraction accuracy

Inactive Publication Date: 2005-11-30
BEIHANG UNIV
View PDF0 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technology of the present invention solves the problem: In order to solve the shortcomings of low precision and poor stability in the existing high-noise image feature point extraction method, the present invention provides a high-noise image feature point automatic extraction method, which is used to extract noise in the target feature and background area. It is used when the interference is large and the edge of the target feature is not easy to extract. It not only has fast measurement speed and high precision, but also can obtain better edge positioning and anti-noise ability

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
  • Strong noise image characteristic points automatic extraction method
  • Strong noise image characteristic points automatic extraction method
  • Strong noise image characteristic points automatic extraction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] Such as figure 1 As shown, the method process of the present invention is to firstly perform preprocessing such as filtering and denoising on the original collected image, and then use the image segmentation method based on the transition region or the image segmentation method based on the background region growth to automatically segment the image and extract the edge, and the image The feature points are extracted from the background, and finally the feature points are curve fitted by iterative least squares, and the analytical form of the feature points corresponding to the surface of the workpiece is calculated. y = Σ i = 0 N a i x i , N is the polynomial highest order

[0021] In the formula, i is the number of edge points, (x, y) is the coordinates of edge points, ...

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

This invention relates to an automatic extraction method for image character dot with high noise, which comprises the following steps: firstly, preprocessing the collected digital image, then dividing the image automatically by method basing on image dividing in transition area or in background area to get the object character area, and then distilling the object character brink dot, finally working out the analysis format of the image character dot by iterative least square curved-fitting method.

Description

Technical field [0001] The invention relates to an image feature point measurement method for online high-precision measurement, in particular to an automatic extraction method for high-noise image feature points. Background technique [0002] With the development of modern processing industry, more and more micro-precision workpieces require high-precision online measurement. However, in the actual online measurement, since the image to be processed is the surface of the metal workpiece captured in real time, the influence of factors such as uneven surface illumination, high reflection of the feature edge, metal texture, edge burrs and stray light, etc., lead to the blurring of the target area in the image. The dynamic range of the grayscale distribution is large, and the grayscale difference between the target area and the background area is not obvious, which makes it difficult to automatically segment the image. [0003] At present, the methods of automatic image segmen...

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): G06K9/46
Inventor 赵慧洁屈玉福
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
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