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

An Image Measurement Algorithm for Dimensions of Circular Industrial Parts

A technology for image measurement and parts, which is applied in the field of image measurement algorithms for the size of circular industrial parts, can solve problems such as difficult image size detection, and achieve high application value, good detection stability and detection accuracy.

Active Publication Date: 2022-03-04
西安大目智能设备研究所有限公司
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Due to the interference of oil pollution factors, it is difficult for image-based size 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
  • An Image Measurement Algorithm for Dimensions of Circular Industrial Parts
  • An Image Measurement Algorithm for Dimensions of Circular Industrial Parts
  • An Image Measurement Algorithm for Dimensions of Circular Industrial Parts

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] Attached below Figure 1-9 The present invention is described in further detail:

[0039] An image measurement algorithm for the size of circular industrial parts, the image measurement algorithm specifically includes the following steps:

[0040] S1: Extract the edge of the image, and calculate the gradient direction of the image edge.

[0041] The calculation method of extracting the edge of the image adopts the CANNY edge detection algorithm commonly used in image processing.

[0042] The calculation method of the gradient direction is as follows:

[0043] First, the image is convolved in the XY direction with a Gaussian differential window. Assuming that the gradients of a point in the image in the X and Y directions are Gx and Gy respectively, the sine and cosine of the direction of the gradient are:

[0044]

[0045]

[0046] S2: Calculate the included angle of the line between the edge of the image and the center of the initial circle.

[0047] The calc...

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 image measurement algorithm for the size of circular industrial parts, including the following steps: extracting the edge of the image, calculating the gradient direction of the edge of the image; calculating the angle between the line between the edge of the image and the center of the initial circle; removing the false artifacts caused by shadows through calculation Edges and too short fine edges; perform binary segmentation on the image, and then remove the connected areas associated with the boundary; segment the part image into regions and obtain accurate boundaries through morphological operations, and implement boundary chain code tracking to obtain candidate incomplete Boundary contour; label each contour segment and perform circle fitting separately; inflate each circle fitting result, and then select the circle that covers the most contour segments; perform ellipse least squares fitting again based on the contour segments covered by the current ring Combine; obtain the major and minor axes of the ellipse, and obtain the detection result; this application obtains a robust fitting of the circular contour when the contour is incomplete by fusing the broken image edge and the circular internal area fragment.

Description

technical field [0001] The invention belongs to the field of image size detection, in particular to an image measurement algorithm for the size of circular industrial parts. Background technique [0002] Circle is the most common shape in industrial scenes, and its size detection is one of the most widely used requirements in industrial vision. [0003] Due to the interference of oil pollution factors, it is difficult to detect the size based on the image. Contents of the invention [0004] The object of the present invention is to provide an image measurement algorithm for the dimensions of circular industrial parts, which obtains a robust fitting of circular contours in the case of incomplete contours by fusing fragmented image edges and circular inner area fragments , thereby improving the detection accuracy. [0005] The purpose of the present invention is achieved through the following technical solutions: [0006] An image measurement algorithm for the size of cir...

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): G01B11/08G01B11/24G06T7/00G06T7/11G06T7/13G06T7/187
CPCG01B11/08G01B11/24G06T7/0004G06T7/13G06T7/11G06T7/187G06T2207/30164
Inventor 田原梁毅军房柱房国华
Owner 西安大目智能设备研究所有限公司