形态滤波在中厚板表面裂纹在线检测中的应用

Application of morphological filtering to on-line detection of surface crack of medium and heavy steel plate

用面阵CCD摄像机采集中厚板表面图像,对采集到的图像进行形态滤波的Top-Hat变换,并结合阈值处理及连通区域搜索等算法,可以在线检测中厚板的各种表面裂纹缺陷,包括横向裂纹、纵向裂纹、星状裂纹等。根据从生产线上采集到的图像分析了中厚板裂纹缺陷的典型特征,并对形态滤波中的结构元素选取进行了研究。该算法已用在中厚板生产线的表面缺陷在线检测系统中。

Surface images of medium and heavy steel plates were captured by CCD area scan camera. Top-Hat transform of morphological filtering was applied to these images. With algorithms of threshold processing and connected region searching, surface cracks of medium and heavy steel plates could be detected on-line, including horizontal cracks, vertical cracks, and star cracks. Based on surface images captured from production line of medium and heavy steel plates, typical features of cracks were analyzed, and selection of structural elements for morphological filtering was studied. The algorithm was applied to the on-line surface inspection system for a production line of medium and heavy steel plates.