알루미늄 표면불량 검사를 위한 영상처리알고리즘 응용에 관한 연구

Abstract

본 연구에서는 알루미늄의 압연 과정에서 발생하는 알루미늄 판재 표면불량을 검출하는 영상처리 알고리즘을 개발하였다. 표면불량의 정상적인 면의 영상과 흠집 영상의 화소 밝기 차이를 이용하여 불량 부분의 경계 부분을 검출하기 위해 다양한 필터를 사용하였다. 먼저 미디언 필터를 이용하여 영상 내의 잡음을 제거하고, 불량의 경계 부분을 강조하기 위하여 Sharpening 필터를 적용하였다. 그리고 Canny 알고리즘을 이용하여 불량 부분의 경계 점들을 검출하였다. 최종적으로 검출된 경계 부분을 포함하는 사각형의 두 좌표를 찾아 원 영상으로부터 불량에 해당하는 영상을 다시 구성하였다.

알루미늄 압연 판재의 서로 다른 표면불량 샘플 4종을 대상으로 제안한 알고리즘을 적용한 결과, 만족할 만한 결과를 얻을 수 있었다.

This study is on the application the image processing algorithm for inspection of the aluminium mill strip surface defect.

The image of surface defect data was obtained using the CCD camera with the digital signal processing board. The edge was found from the difference of pixel intensity between the normal image and the defect image.

Two steps were taken to find the edge in the image processing algorithm.

Frist, noise was removed by using the median filter in the image. Canny Algorithm was used to defect the exact edge.

The defect image section was separated from the original image is to find the coordination point p1 and p2 which include the defect image.

Experiments showed that this algorithm is useful enough to inspect the defects.

This study is on the application the image processing algorithm for inspection of the aluminium mill strip surface defect.

The image of surface defect data was obtained using the CCD camera with the digital signal processing board. The edge was found from the difference of pixel intensity between the normal image and the defect image.

Two steps were taken to find the edge in the image processing algorithm.

Frist, noise was removed by using the median filter in the image. Canny Algorithm was used to defect the exact edge.

The defect image section was separated from the original image is to find the coordination point p1 and p2 which include the defect image.

Experiments showed that this algorithm is useful enough to inspect the defects.