Paper
13 June 2024 Research on high-precision workpiece size measurement based on grayscale moment algorithm
Jiacheng Liu, Jiahao Yu, Liankai Wang, De Song
Author Affiliations +
Proceedings Volume 13180, International Conference on Image, Signal Processing, and Pattern Recognition (ISPP 2024); 131803O (2024) https://doi.org/10.1117/12.3033730
Event: International Conference on Image, Signal Processing, and Pattern Recognition (ISPP 2024), 2024, Guangzhou, China
Abstract
In response to the issues of low accuracy and significant errors in manual measurements of high-precision workpieces, this paper proposes a high-precision, low-error dimension measurement algorithm. Focusing on triangular workpieces as the detection target, the proposed algorithm first applies threshold segmentation to the workpiece image, and then it employs an improved grayscale moment algorithm to identify sub-pixel edges. Subsequently, it uses an eight-neighborhood algorithm combined with Hough transform for rough line fitting and, finally, employs the RANSAC algorithm along with the least squares method for precise line fitting. After multiple measurements of the workpiece, experimental results demonstrate that the proposed algorithm achieves high-precision dimension measurement with a minimum error of 0.467 μm and an average error of 1.439 μm.
(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.
Jiacheng Liu, Jiahao Yu, Liankai Wang, and De Song "Research on high-precision workpiece size measurement based on grayscale moment algorithm", Proc. SPIE 13180, International Conference on Image, Signal Processing, and Pattern Recognition (ISPP 2024), 131803O (13 June 2024); https://doi.org/10.1117/12.3033730
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Detection and tracking algorithms

Image processing

Image segmentation

Hough transforms

Image processing algorithms and systems

Edge detection

Data modeling

Back to Top