Method and apparatus for detecting edge

An edge detection and edge direction technology, applied in the multimedia field, can solve the problem of poor edge detection effect, achieve the effect of shielding noise, retaining image information, and good image information

Active Publication Date: 2009-01-28
HUAWEI TECH CO LTD
View PDF0 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the formula for calculating g1(x, y) or g2(x, y) in the prior art, a second-order gradient operator is used, which is sensitive to noise, so it is easy to cause misjudgment or missed judgment when performing edge detection. leading to poor edge detection

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
  • Method and apparatus for detecting edge
  • Method and apparatus for detecting edge
  • Method and apparatus for detecting edge

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0037] figure 2 A schematic flow chart of an edge detection method provided by an embodiment of the present invention, the method includes:

[0038] S1. Determine the decision window, the decision window is a pixel block of N*N size, wherein N is an odd number, and N is greater than 1;

[0039] In the embodiment of the present invention, a square window with an odd number of sizes is used as a decision window to determine whether the center pixel of the decision window is an edge pixel. The selection of the decision window can be determined by resource consumption and application scenarios. The larger the window, the more resources are consumed, but the shielding effect on large particle noise is also better. For example, a judgment window with a size of 5×5, 7×7 or 9×9 can be used, where the size is represented by pixels, and a judgment window of 5×5 means that the window contains 25 pixels with 5 rows and 5 columns. pixels.

[0040] S2. Divide the decision window into d...

Embodiment 2

[0082] The edge detection method of the present invention is introduced below with a specific application example.

[0083] Take the detection of the 0 degree, 90 degree, 45 degree and 135 degree edge of the image with post-noise with a 5×5 decision window as an example. The original image is shown in Figure 5, which is polluted by certain Gaussian noise.

[0084] Step 1. Select a 5×5 decision window;

[0085] Step 2, the division of edge blocks in the decision window, the specific division method is the same as that shown in Figure 3:

[0086] Step 3. Calculate the block variance of each edge direction, which is the same as described above.

[0087] Step 4. Judging the result according to the block variance. A unified threshold T=10000 is set here, and the judgment results for each direction are shown in Figure 6, Figure 6(a) is the horizontal edge judgment result, Figure 6(b) is the vertical edge judgment result, and Figure 6(c) is 45 Figure 6(d) shows the judgment result...

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 embodiment of the invention discloses a method and a device for detecting edges. The method comprises the following steps that: a decision window is determined; the decision window is a pixel block with the size of NxN, wherein N is an odd number and more than one; the decision window is divided into different edge blocks according to different edge directions; block variances in the corresponding edge directions are calculated according to the edge blocks; whether a central pixel point of the decision window is an edge pixel point is judged according to the block variances. The technical proposal has the following advantages that when the method based on the block variances is adopted for detecting edges, noise can be effectively shielded, so as to obtain the accurate image edges and preserve good image information.

Description

technical field [0001] The invention relates to the field of multimedia technology, in particular to an edge detection method and device. Background technique [0002] Image edge detection is an important branch in the field of digital image processing, especially with the rapid development of the computer field in recent years, people's requirements for image quality are getting higher and higher, and image edge detection processing has become a research hotspot. Edge detection is often used in image enhancement and noise reduction, image interpolation calculation and other technologies. [0003] The current edge detection usually uses Sobel edge detection operator, Sobel template such as figure 1 as shown, figure 1 The value in represents the weighting coefficient corresponding to each pixel, where figure 1 (a) represents the template in the vertical direction, figure 1 (b) represents the template in the horizontal direction. For vertical templates there are: [0004...

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): G06T5/00G06K9/46
Inventor 邓安刚
Owner HUAWEI TECH CO LTD
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