지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
논문 기본 정보
- 자료유형
- 학술대회자료
- 저자정보
- 저널정보
- 한국정보기술학회 Proceedings of the International Conference on Smart Mobility And Revolutionary Transportation Proceedings of the 5th International Conference on Smart Mobility And Revolutionary Transportation (SMART 2024)
- 발행연도
- 2024.12
- 수록면
- 69 - 73 (5page)
이용수
초록· 키워드
오류제보하기
This paper explores the feasibility of applying super-resolution technology for defect detection in industrial products. The aim of the research is to assess the suitability of super-resolution results based on the degree of resolution enhancement and to improve defect detection performance. For this purpose, industrial product data was used to conduct experiments. The results were recon-structed by removing low-frequency areas and applying the super-resolution model SRGAN to enhance the resolution of defect images. The images were then compared at the original size and 2x and 4x increased resolutions. The experimental results showed that the outcome with 2x resolution enhancement achieved the highest performance with an AUC of 98.4% and an EER of 0.085. This suggests that the application of super-resolution technology is effective in defect detection. Therefore, applying super-resolution technology can be an important method to enhance the accuracy of defect detection and production efficiency in industrial products.
목차
Abstract
1. Introduction
2. Related Works
3. Proposed Method
4. Conclusions
References
참고문헌 (0)
참고문헌 신청이 논문의 저자 정보
이 논문과 함께 이용한 논문
최근 본 자료
댓글(0)
0
UCI(KEPA) : I410-151-25-02-092148287