영상 처리를 이용한 슬라브 결함 검출 알고리즘 개발

Abstract

In recent years, automated inspection systems have become widely used to create high-quality products and achieve high productivity in various industries. The detection of defects on steel surfaces is an important component of the steel making process to control the quality of steel products. However, detection of defects in steel slab is still carried out by human inspection. This thesis proposed an algorithm to detect defects such as edge defects and oscillation marks in slab through the use of image processing. The surface of a slab is partially covered with scales composed of oxidized substance. Because these scales can be visually similar to defects, and because the surface features of slab images vary under different lighting conditions, defect detection can be difficult. To minimize the influence of scales and to improve the accuracy of detection, a new detection method is proposed. The edge defects are extracted by vertical projection profile and canny edge detection. Also, the reconstructed images by discrete wavelet transform are used for defect detection of oscillation mark. Finally, the experimental results show the effectiveness of the proposed algorithm.