이미지 처리를 이용한 슬라브 표면 핀홀 결함 검출 기법

Abstract

In this paper, we introduce an image-processing algorithm that detects pinholes in steel slabs. Because the pinhole is relatively small and similar to noise components, it is difficult to distinguish pinhole from a steel slab surface. To increase detection accuracy, we propose a new algorithm for pinhole detection. We applied Gabor filters to extract defect candidates and subsequently developed a mask to score the specific features of each pinholes. The performance of the proposed algorithm was evaluated on 1764 subimages

116 of these images had pinholes, and the rest of the images were free of defects. The proposed algorithm has 87.1% accuracy for the detection of pinhole images and false alarm is 3.8%.