Unlock instant, AI-driven research and patent intelligence for your innovation.

Method and device for edge detection

A boundary detection and boundary technology, which is applied in the field of image processing, can solve problems such as affecting recognition, inaccurate boundary detection, and increasing the influence of boundary detection in stained areas, so as to achieve the effect of improving accuracy and reducing influence

Active Publication Date: 2020-01-14
SHENZHEN YIHUA COMP +2
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] However, when there are stains in the detected image, the above method may determine both the stained area and the foreground image area as black or white when the image is binarized, increasing the impact of the stained area on boundary detection , causing the row projection difference between the row where the upper or lower border of the stain is located and the adjacent row to be greater than the set threshold, or the column projection difference between the column where the left or right border of the stain is located and the adjacent column is greater than Set the threshold and determine the boundary of the stained area as the boundary of the foreground image, which cannot accurately detect the boundary, which will affect the subsequent recognition

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 device for edge detection
  • Method and device for edge detection
  • Method and device for edge detection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0022] figure 1 It is a flow chart of a method for boundary detection provided by Embodiment 1 of the present invention. This embodiment is applicable to the situation where boundary detection needs to be performed on an image. The method can be performed by a device for boundary detection, which can be controlled by software and\ or hardware components. The method provided in this embodiment specifically includes the following steps:

[0023] Step 110, acquiring a grayscale image corresponding to the image to be detected.

[0024] Preferably, the image to be detected is an image of a preset area in the original image corresponding to the foreground image whose boundary needs to be determined, so that in the subsequent boundary detection process, the interference information of other area images in the original image is reduced. Wherein, the preset area includes the foreground image that needs to determine the boundary.

[0025] If the original image is an image including a...

Embodiment 2

[0048] figure 2 It is a flowchart of a boundary detection method provided by Embodiment 2 of the present invention. This embodiment is further optimized on the basis of the foregoing embodiments. The method provided in this embodiment specifically includes the following steps:

[0049] Step 210, acquiring a grayscale image corresponding to the image to be detected.

[0050] Step 220, determine the boundary detection range.

[0051] In this embodiment, the boundary detection range includes: an upper boundary detection range and a lower boundary detection range.

[0052] Step 230, acquiring a pixel within the boundary detection range in the grayscale image as a target pixel.

[0053] Preferably, after the upper boundary detection range or the lower boundary detection range is determined, each pixel point within the upper boundary detection range or the lower boundary detection range is traversed, and the traversed current pixel point is used as the target pixel point.

[00...

Embodiment 3

[0077] image 3It is a flow chart of a boundary detection method provided by Embodiment 3 of the present invention, and this embodiment is further optimized on the basis of the foregoing embodiments. The method provided in this embodiment specifically includes the following steps:

[0078] Step 310, acquiring a grayscale image corresponding to the image to be detected.

[0079] Step 320, determine the boundary detection range.

[0080] In this embodiment, the boundary detection range includes: a left boundary detection range and a right boundary detection range.

[0081] Step 330, acquiring a pixel within the boundary detection range in the grayscale image as the target pixel.

[0082] Preferably, after the left boundary detection range or the right boundary detection range is determined, each pixel point within the left boundary detection range or the right boundary detection range is traversed, and the current pixel point traversed is used as the target pixel point.

[0...

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

An embodiment of the invention discloses a boundary testing method and a boundary testing device. The boundary testing method comprises the steps of acquiring a gray-scale map which corresponds with a to-be-tested image; determining a boundary testing range, calculating a boundary determining direction gray-scale increment which corresponds with each pixel according to a gray-scale difference between each pixel in the boundary testing range and an adjacent pixel in a boundary determining direction in the gray-scale map; and testing a boundary position which matches the boundary determining direction in the gray-scale map according to the boundary determining direction gray-scale increment which corresponds with each pixel. The method provided by the invention settles a problem of incapability of accurately determining a foreground image boundary on the condition that a dirt exists in the to-be-tested image in prior art, and realizes direct boundary determining through the gray value of the pixel in the gray-scale map. On the condition that the dirt exists in the to-be-tested image, influence of the dirt in the boundary testing process is reduced, and boundary determining accuracy is improved, thereby eliminating more interference information for subsequent recognition.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of image processing, and in particular, to a method and device for boundary detection. Background technique [0002] With the continuous development of science and technology, images have become an important source of information for people. Among them, image boundary detection technology is the basis of image processing technologies such as image measurement, pattern recognition and image segmentation. [0003] An image frame includes a foreground image and a background image. For example, in an image containing a human face, the foreground image refers to the area covered by the human face, and the background image refers to the area other than the human face. The purpose of boundary detection is mainly to determine the boundary of the foreground image in the image, and then further identify the foreground image within the boundary according to the determined boundary. [0004] The ...

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 王晓琳
Owner SHENZHEN YIHUA COMP