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

Image edge extraction method and system based on structure constraint clustering

An image edge and structural constraint technology, applied in the field of image processing, can solve problems such as lack of edge detection accuracy, achieve strong universality and eliminate noise interference.

Active Publication Date: 2021-08-20
INST OF SOFTWARE - CHINESE ACAD OF SCI
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Traditionally implemented edge detection algorithms include canny operator, sobel operator, Prewitt operator, etc., as well as some edge detection methods based on deep learning, but none of them have sufficient edge detection accuracy.

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
  • Image edge extraction method and system based on structure constraint clustering
  • Image edge extraction method and system based on structure constraint clustering
  • Image edge extraction method and system based on structure constraint clustering

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0043] Such as figure 1 As shown, a kind of image edge extraction method based on structural constraint clustering that the embodiment of the present invention provides, comprises the following steps:

[0044] Step S1: Collect the image of the object whose edge needs to be extracted, and obtain the image in the frontal direction of the object as the original image; perform grayscale processing on the original image to obtain a grayscale image; perform thresholding processing on the grayscale image, and obtain the thresholded image It has two gray values ​​of light and dark;

[0045] Step S2: Put the thresholding map into a plane Cartesian coordinate system, obtain the coordinates of each pixel, and construct a coordinate thresholding map;

[0046] Step S3: using a density clustering method to cluster the pixels in the coordinateized thresholded image into pixel clusters;

[0047] Step S4: For pixel clusters, perform cluster optimization under structural knowledge constraints...

Embodiment 2

[0113] Such as Figure 15 As shown, the embodiment of the present invention provides an image edge extraction system based on structural constraint clustering, including the following modules:

[0114] Obtaining a thresholded image module 71, used to collect an object image that needs to extract an edge, and obtain an image in the front view direction of the object as an original image; perform grayscale processing on the original image to obtain a grayscale image; perform thresholding processing on the grayscale image, The resulting thresholded image only has two gray values ​​of light and dark;

[0115] Obtaining the thresholded map coordinate module 72, used to put the thresholded map into a plane Cartesian coordinate system, obtain the coordinates of each pixel, and construct a coordinateized thresholded map;

[0116] Obtaining a pixel cluster module 73, configured to use a density clustering method to cluster the pixels in the coordinateized thresholded image into pixel ...

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 an image edge extraction method and system based on structure constraint clustering, and the method comprises the steps: S1, carrying out the graying processing of an original image, and obtaining a gray-scale image; carrying out thresholding processing on the grey-scale image to obtain a thresholding image; s2, putting the thresholding graph into a rectangular plane coordinate system, and constructing a coordinate thresholding graph; s3, using a density clustering method to cluster pixels in the coordinate thresholding image into a pixel cluster; s4, carrying out cluster optimization on the pixel clusters under structural knowledge constraints, and obtaining edge clusters containing object edges; s5, removing internal points contained in the edge cluster to obtain a preliminary image edge extraction result; s6, according to the preliminary image edge extraction result,adopting edge correction based on image search to obtain a final image edge extraction result. According to the method provided by the invention, the automation degree of traditional edge detection is improved, and the extraction of the object edge is more efficient and accurate.

Description

technical field [0001] The invention relates to the field of image processing, in particular to an image edge extraction method and system based on structural constraint clustering. Background technique [0002] Edge detection is a basic tool in image processing, computer vision, and machine vision. It is usually used for feature extraction and feature detection. It aims to detect edges or discontinuous areas that have obvious changes in a digital image. In one-dimensional space In , a similar operation is called step detection. An edge is a boundary line between different regions in an image, and usually an edge image is a binary image. The purpose of edge detection is to catch areas with sharp changes in brightness, which are usually our focus. A two-degree discontinuity in an image is usually one of the following: image depth discontinuity, image (gradient) orientation discontinuity, image illumination (intensity) discontinuity, or texture change. [0003] Ideally, app...

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): G06T7/13G06T7/136G06K9/62
CPCG06T7/13G06T7/136G06F18/23
Inventor 张常有薄文蔡晓峰武文佳田卓
Owner INST OF SOFTWARE - CHINESE ACAD OF SCI
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