TY - GEN
T1 - Visual Measurement Technology for Heterogeneous Material Gaps Based on Adaptive Threshold Segmentation
AU - He, Kunhuan
AU - Zou, Dongyi
AU - Jin, Xin
AU - Zhu, Rongquan
AU - Xu, Jintong
AU - Li, Chaojiang
N1 - Publisher Copyright:
© 2025 IEEE.
PY - 2025
Y1 - 2025
N2 - The accurate measurement of gasket placement gap widths during the assembly and alignment of optical systems can significantly enhance the efficiency of the entire process. As the gap consists of two materials with differing properties, the degree of light reflection varies when illuminated, complicating visual measurement. This paper presents a visual measurement technique based on an adaptive threshold segmentation method, addressing the challenges of inconsistent reflectivity and edge detection in the measured gap region. The introduction of the RANSAC fitting algorithm improves edge fitting quality and enhances measurement accuracy. Experimental results demonstrate that the accuracy of this measurement algorithm exceeds 8 μm, with measurement consistency surpassing 3 μ m, thus meeting the required standards for accuracy and consistency.
AB - The accurate measurement of gasket placement gap widths during the assembly and alignment of optical systems can significantly enhance the efficiency of the entire process. As the gap consists of two materials with differing properties, the degree of light reflection varies when illuminated, complicating visual measurement. This paper presents a visual measurement technique based on an adaptive threshold segmentation method, addressing the challenges of inconsistent reflectivity and edge detection in the measured gap region. The introduction of the RANSAC fitting algorithm improves edge fitting quality and enhances measurement accuracy. Experimental results demonstrate that the accuracy of this measurement algorithm exceeds 8 μm, with measurement consistency surpassing 3 μ m, thus meeting the required standards for accuracy and consistency.
KW - adaptive threshold segmentation
KW - optical system
KW - RANSAC fitting algorithm
KW - visual measurement
UR - https://www.scopus.com/pages/publications/105038110716
U2 - 10.1109/ICEMCE68156.2025.11466515
DO - 10.1109/ICEMCE68156.2025.11466515
M3 - Conference contribution
AN - SCOPUS:105038110716
T3 - 2025 9th International Conference on Electrical, Mechanical and Computer Engineering, ICEMCE 2025
SP - 96
EP - 100
BT - 2025 9th International Conference on Electrical, Mechanical and Computer Engineering, ICEMCE 2025
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2025 9th International Conference on Electrical, Mechanical and Computer Engineering, ICEMCE 2025
Y2 - 17 October 2025 through 19 October 2025
ER -