Image edge detection method based on neighbourhood dispersion

A technology of neighborhood dispersion and image edge, applied in image analysis, image data processing, instruments, etc., to avoid interruption of image contours

Active Publication Date: 2016-07-06
西安深信科创信息技术有限公司
View PDF3 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to provide a kind of image edge detection method based on neighborhood dispersion, s

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 detection method based on neighbourhood dispersion
  • Image edge detection method based on neighbourhood dispersion
  • Image edge detection method based on neighbourhood dispersion

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0034] The present invention will be described in detail below with reference to the drawings and specific embodiments.

[0035] The image edge detection method of the present invention based on neighborhood dispersion is implemented according to the following steps:

[0036] Step 1) Convert the original color image into a single-channel 8-bit grayscale image, the grayscale of the 8-bit grayscale image is between 0-255;

[0037] Step 2) Find the dispersion coefficient matrix M of the eight-bit grayscale image. The dimension of the dispersion coefficient matrix M is consistent with the size of the original image.

[0038] Set as a 2×2 sampling template for grayscale images, such as figure 1 Shown, z i To sample the gray value of each pixel in the template, use the sample template to move from the first row and the first column of the image column by column row by row, calculate the average deviation of each pixel and save it in the dispersion coefficient matrix The corresponding positi...

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 an image edge detection method based on neighbourhood dispersion. The image edge detection method comprises the following steps: 1) transforming an original colorful image into a single-channel eight-bit gray level image; 2) obtaining the dispersion coefficient matrix M of the eight-bit gray level image; 3) executing a horizontal direction refining operation for the dispersion coefficient matrix M to obtain a matrix Mh; 4) executing a vertical direction refining operation for the dispersion coefficient matrix M to obtain a matrix Mv; 5) combining the matrix Mh with the matrix Mv, and combining all points which are equal to 1 in the two matrixes to obtain a rough refining edge matrix O; and 6) carrying out precise processing and redundant information filtering on an image outline by the rough refining edge matrix O according to an orientation gradient to obtain an outline matrix, and finally, carrying out transformation through the outline matrix to obtain a binary edge image. The method disclosed in the invention is simple and easy in implementation and guarantees the accuracy of the outline.

Description

technical field [0001] The invention belongs to the technical field of image edge detection, and realizes non-threshold, isotropic edge detection that ensures the continuity of object outlines in images, and in particular relates to an image edge detection method based on neighborhood dispersion. Background technique [0002] The purpose of image segmentation is to separate the objects in the image from the background area. The segmentation technology can be summarized into three steps, namely filtering, enhancement, and edge detection. At present, there are several mature commonly used operators such as Sobel, Prewitt, Roberts, Laplace, Canny, etc., and these operators are all neighborhood-based methods. Among them, the Sobel, Prewitt, and Roberts operators are all first-order linear discrete difference operators. The first two need to calculate the brightness difference values ​​in the X direction and the Y direction when detecting the edge of the image, and Prewitt detect...

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): G06T7/00G06T7/13G06T7/181
Inventor 孙钦东姚强兀华王倩
Owner 西安深信科创信息技术有限公司
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