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
- 문서 유형
- 연구출판물 · 학술지 논문
- 등재
- KCIScopus
- 저널 순위
- Scopus Q4KCI Q4
- 저널
- 한국정밀공학회지42(2) · pp.139 · 2025
- 피인용
- Scopus 1KCI 1
- FWCI (Scopus)
- 0.19
- ISSN
- 1225-9071
저자
- 채종혁제1저자Industrial Big Data Convergence Research Center, Korea Electronics Technology Institute
- 이동규Industrial Big Data Convergence Research Center, Korea Electronics Technology Institute
- 오승훈Industrial Big Data Convergence Research Center, Korea Electronics Technology Institute
- 노유정교신저자School of Mechanical Engineering, Pusan National University
초록
In this study, we propose a deep learning-based method for large-area inspection aimed at the high-speed detection ofmicro hole diameters. Micro holes are detected and stored in large images using YOLOv8, an object detection model. Asuper-resolution technique utilizing ESRGAN, an adversarial neural network, is applied to images of small micro holes,enhancing them to high resolution before measuring their diameters through image processing. When comparing thediameters measured after 8x super-resolution with the results from existing inspection equipment, the average error rate isremarkably low at 0.504%. The time taken to measure an image of one micro hole is 0.470 seconds, which is ten timesfaster than previous inspection methods. These results can significantly contribute to high-speed measurement and qualityimprovement through deep learning.
키워드
Silicon cathodeVision inspectionObject detectionSuper resolutionMicro hole diameter실리콘 캐소드비전 검사객체 검출초해상화미세 구멍 직경
식별자
- Scopus EID
- 2-s2.0-85218981164
- KCI
- ART003172208



로그인
연구물 목록으로