검색 상세

오토 인코더와 단일클래스 SVM을 적용한 결함 검출 연구

A Defect Detection Method Using Auto-Encoder and One-Class SVM

초록/요약

In this paper, we propose a new defect detection method using a deep autoencoder and one-class support vector machine. The proposed method extracts patches in insert images and classi es each patch into normal and defect one. However, the appearance of defects varies from case to case and it is very dicult to collect all possible defect patch images, which hinders the use of conventional binary classi cation methods. Therefore, we develop a novel method that only requires normal patches. To be precise, the method uses a deep auto-encoder as a feature extractor, which is trained with only normal patches, and one-class SVM is adopted to determine the decision boundary of normal cases. Experimental results show that the proposed method works robustly for light changes and improves the classi cation performance compared with conventional methods.

more

목차

제1장 서론
1.1 연구배경
1.2 연구내용
1.3 논문구성

제2장 제품영상기반 결함 검출 방법
2.1 결함 검출 방법의 구성
2.2 패치 추출 과정
2.3 특징 추출 과정
2.4 결함 분류 과정

제3장 실험결과
3.1 실험데이터 세트
3.2 오토인코더 및 단일 클래스 SVM 세팅
3.3 분류결과
3.4 실험결과 분석 및 토의

제4장 결론

참고문헌

Abstract

more