基于向量的带钢缺陷检测算法

Strip Defect Detection Algorithm Based on Vector

介绍了用计算机视觉检测系统中的图像处理技术检测带钢的边裂以及孔洞。首先识别带钢图像的轮廓,得到带钢边部、孔洞的轮廓曲线向量编码,然后利用向量的点积计算轮廓的弯曲程度,据此作为判断条件,检测边裂与孔洞缺陷。实验结果表明:该方法应用到实际检测系统中,能够可靠地检出带钢的边裂。

This paper introduces the detection system for strip edge cracks and holes based on the image processing techniques of computer vision.First,it identifies the strip contour images to get the vector code of the edge and holes contour curves,then the vector dot product is used to calculate contour of bending degree which is accordingly as a condition of judgment,to detect edge crack and hole defect.Experimental results show that the method can be reliably detecting the strip edge cracking in the actual detection system.