We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Detection method of roundness of steel collar inner ring based on machine vision.
- Authors
JIN Shoufeng; JIAO Hang
- Abstract
To solve the problems of unstable accuracy, low efficiency and large subjective error of manual contact detection for the roundness of steel collar inner ring, a detection method based on machine vision was proposed. By establishing a machine vision detection platform for the roundness of steel collar inner ring, the image of steel collar under backlight imaging was obtained. The edge of the inner ring of the steel collar was roughly positioned at the pixel level by Sobel operator. On this basis, the optimum step threshold of the foreground and background of the image of the steel collar was determined by the maximum interclass variance method, which was used as the judgment condition of Zernike moment edge model to extract the sub-pixel edge points of the inner ring of the steel collar. The ideal center of the sub-pixel edge of the collar inner ring was obtained by the least square method, and the mathematical model of the roundness of the collar inner ring was established based on the image information of the collar, and the non-contact measurement of the roundness of the collar inner ring was realized. The experimental results show that the maximum deviation of the roundness of the inner ring of the steel collar PG1-4554 is 0. 004 mm, and the maximum deviation of the traditional method is 0. 007 mm, and the accuracy is improved by 42%.
- Subjects
COMPUTER vision; STEEL; LEAST squares; ROUNDNESS measurement; VISION
- Publication
Wool Textile Journal, 2022, Vol 50, Issue 4, p83
- ISSN
1003-1456
- Publication type
Article
- DOI
10.19333/j.mfkj.20210801106