Micron-scale edge detection method for backlit images

An edge detection, micron-level technology, applied in image analysis, image data processing, instruments, etc., to achieve fast solution speed, improve accuracy, and reduce computational complexity

Active Publication Date: 2017-10-31
SHENYANG POLYTECHNIC UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

These methods work well for front-illuminated images, none of which are suitable for micron-scale edge detection on back-lit images

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
  • Micron-scale edge detection method for backlit images
  • Micron-scale edge detection method for backlit images
  • Micron-scale edge detection method for backlit images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0056] As shown in the figure, the present invention comprises the following steps:

[0057] 1. Combining the point spread function and the unilateral step model, construct the normal distribution function model of the backlight image step edge normal plane section line.

[0058] The foreground and background of the backlight edge detection image are constant P 1 ,P 2 , as attached figure 1 As shown, the gray level difference between background and foreground is

[0059] g=P 2 -P 1

[0060] The intercept line of the gray surface through the edge normal plane is a normal distribution function (Gaussian integral) curve:

[0061]

[0062] but

[0063]

[0064] The projection of the image edge point through the center point of the curve on the image plane, ( or t-μ=0)

[0065] 2. Surface fitting solution of discrete points in the transition zone

[0066] In order to simplify the surface model, make μ, σ linearly change in the small neighborhood along the edge line...

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 micron-level edge detection method of a backlight image belongs to the technical field of high-precision detection, and in particular relates to a micron-level edge detection method of a backlight image. The invention provides a micron-level edge detection method of a backlight image with high precision of surface fitting and anti-interference. The present invention comprises the following steps: 1) Combining the point spread function and the unilateral step model, constructing a backlight image step edge normal plane section line normal distribution function model; the foreground and background of the backlight edge detection image are constants P1, P2, The grayscale difference between the background and the foreground is g=P2-P1, and the intercept line of the grayscale surface crossing the edge normal plane is a normal distribution function (Gaussian integral) curve: then the projection of the center point of the image edge point passing the curve at the image plane, Or t-μ=0.

Description

technical field [0001] The invention belongs to the technical field of high-precision detection, and in particular relates to a micron-level edge detection method of a backlight image. Background technique [0002] The machine vision measurement system integrates multi-field and multi-disciplinary key technologies such as optics, sensors, image processing and pattern recognition, and is widely used in the field of non-contact high-speed online measurement. The invention utilizes machine vision and digital image processing technology to establish a normal normal probability distribution curve image edge grayscale surface model for backlit digital images, uses the least square method to obtain four coefficients of the fitting surface, and obtains micron-level sub-pixel edges . [0003] Patent application number: 2011104481191, titled "A Color Image Edge Detection Method", which decomposes a color image into four channel images of red, green, blue and yellow, calculates the re...

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): G06T7/13
Inventor 赵文辉赵文珍段振云王宁
Owner SHENYANG POLYTECHNIC 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