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

Image edge detection method and device based on Canny algorithm

An image edge and detection method technology, applied in the field of image processing, can solve problems such as threshold setting relying on experience, edge blur detection, noise influence, etc.

Inactive Publication Date: 2017-10-24
HUANGHE S & T COLLEGE
View PDF3 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although the traditional Canny algorithm has great advantages in image edge detection compared with the Prewitt algorithm and Sobel algorithm, it has disadvantages such as serious noise influence, blurred detection edge, and excessive dependence on experience in threshold setting.

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 and device based on Canny algorithm
  • Image edge detection method and device based on Canny algorithm
  • Image edge detection method and device based on Canny algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0166] In order to verify the processing effect of the algorithm proposed in this paper, the algorithm proposed in this paper, the traditional Sobel algorithm and the Laplace algorithm are respectively used to process a lidar image and a Lena image. The processing results are shown in Figure 1 and Figure 2. in Figure 1a with Figure 2a for the original graph, Figure 1b with Figure 2b It is the processing result graph using the algorithm in this paper, Figure 1c with Figure 2c is the result graph processed by Sobel algorithm, Figure 1d with Figure 2d It is the result graph processed by Laplace algorithm.

[0167] It can be seen from the test results that the three methods can extract the edge information of the object in the image to varying degrees. The Sobel algorithm can reliably extract the edges with obvious contrast, but the loss of edges with inconspicuous contrast is serious. The edge extraction effect of the Laplace algorithm is better than that of the S...

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 a Canny algorithm. The method comprises the steps of image smoothing, gradient magnitude calculation, non-maxima suppression, high and low double-threshold processing and the like. The invention provides an image edge detection method and device for a laser radar distance image in combination with an improved loop filter algorithm and an adaptive Canny algorithm. Noise is filtered by using the improved loop filter algorithm, so that information of a slender structure and the like reflecting key characteristics of an image in the image is effectively protected while the noise is suppressed; according to two indicators including an information entropy and a standard deviation, the algorithm has a higher information entropy value and a lower standard deviation; and by intuitively observing the edge detection results of the three algorithms, the algorithm of the invention can filter noise data more effectively and reflect detail information of the image clearly over the other two algorithms.

Description

technical field [0001] The invention belongs to the field of image processing, and in particular relates to an image edge detection method and device based on Canny algorithm, which are suitable for lidar range image edge detection. Background technique [0002] Due to its high resolution and strong anti-interference ability, lidar has been widely used in the fields of weapon guidance, three-dimensional mapping and aerospace. Lidar is different from ordinary microwave radar. Its imaging results include intensity images and range images. Currently, the processing methods for intensity images have been extensively studied, but there are relatively few studies on range images. The distance image can reflect the distance information between different objects, and combined with the intensity image can obtain the three-dimensional information in the detection area, so it is necessary to process the distance image. [0003] Edge detection refers to the use of image discontinuity t...

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): G06T7/13G06T7/136G06N3/00
CPCG06N3/006G06T7/13G06T7/136G06T2207/10004G06T2207/20182
Inventor 代文征杨勇耿丽君
Owner HUANGHE S & T COLLEGE
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