Skip to main navigation Skip to main content
  • E-Submission

JKSPE : Journal of the Korean Society for Precision Engineering

OPEN ACCESS
ABOUT
BROWSE ARTICLES
EDITORIAL POLICIES
FOR CONTRIBUTORS
REGULAR

딥러닝 기반 실리콘 캐소드 미세 구멍 가공 치수의 대면적 검사 방법

Large-area Inspection Method for Machined Micro Hole Dimension Measurement Using Deep Learning in Silicon Cathodes

Journal of the Korean Society for Precision Engineering 2025;42(2):139-145.
Published online: February 1, 2025

1 한국전자기술연구원 산업데이터융합연구센터

2 부산대학교 기계공학부

1 Industrial Big Data Convergence Research Center, Korea Electronics Technology Institute

2 ISchool of Mechanical Engineering, Pusan National University

• Received: September 19, 2024   • Revised: November 11, 2024   • Accepted: November 20, 2024

Copyright © The Korean Society for Precision Engineering

This is an Open-Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/3.0) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.

  • 32 Views
  • 0 Download
  • 1 Crossref
  • 1 Scopus
prev next

Citations

Citations to this article as recorded by  Crossref logo
  • A Review of Intelligent Machining Process in CNC Machine Tool Systems
    Joo Sung Yoon, Il-ha Park, Dong Yoon Lee
    International Journal of Precision Engineering and Manufacturing.2025; 26(9): 2243.     CrossRef

Download Citation

Download a citation file in RIS format that can be imported by all major citation management software, including EndNote, ProCite, RefWorks, and Reference Manager.

Format:

Include:

Large-area Inspection Method for Machined Micro Hole Dimension Measurement Using Deep Learning in Silicon Cathodes
J. Korean Soc. Precis. Eng.. 2025;42(2):139-145.   Published online February 1, 2025
Download Citation

Download a citation file in RIS format that can be imported by all major citation management software, including EndNote, ProCite, RefWorks, and Reference Manager.

Format:
Include:
Large-area Inspection Method for Machined Micro Hole Dimension Measurement Using Deep Learning in Silicon Cathodes
J. Korean Soc. Precis. Eng.. 2025;42(2):139-145.   Published online February 1, 2025
Close

Figure

  • 0
  • 1
  • 2
  • 3
  • 4
  • 5
  • 6
  • 7
  • 8
  • 9
Large-area Inspection Method for Machined Micro Hole Dimension Measurement Using Deep Learning in Silicon Cathodes
Image Image Image Image Image Image Image Image Image Image
Fig. 1 Si-Cathode specimen
Fig. 2 Method for measuring micro hole diameter using existing inspection equipment
Fig. 3 The proposed process of this study
Fig. 4 Hole Image processing procedure
Fig. 5 Comparison of image processing results boxplot
Fig. 6 Example of labeling data used for learning micro hole detection
Fig. 7 Micro hole data using super-resolution techniques
Fig. 8 Large-area image-based object detection experiment
Fig. 9 Comparison before and after super resolution
Fig. 10 Comparison before and after super resolution
Large-area Inspection Method for Machined Micro Hole Dimension Measurement Using Deep Learning in Silicon Cathodes

Comparison of measured diameter

Mean [mm] Standard dev. [mm] Mean error rate [%]
Measured diameter 454.5 0.508 -
Estimated diameter 454.4 0.634 0.151

Comparison of super-resolution results

No SR x4 x8
Pixel resolution 12.85 5.01 2.5
Error [%] 0.7072 0.544 0.5042
Time [s/image] 0.001 0.32 0.47
Table 1 Comparison of measured diameter
Table 2 Comparison of super-resolution results