摘要
在带钢表面质量视觉检测过程中,一些低对比度缺陷图像应用梯度算子进行分割时,往往找不到图像中的缺陷,从而出现漏检的情况。为了改善带钢图像中低对比度缺陷的分割效果,提出了一种基于扫描线的阈值图像分割算法,该算法可以有效实现平整花、点划伤等低对比度缺陷的分割,同时也能较好地实现对其他缺陷的分割。
During the quality inspection of steel strip surface, some low contrast defect images cannot be found when the inspection system employs the grad operator to segment images. It would result in some undetected errors. In order to improve the segmentation resuh of low contrast defects, a method based on the threshold of the scan lines was proposed. Defects like unknit and dot scratches can be segmented effectively by this method. It is also useful for the segmentation of other defects.
出处
《宝钢技术》
CAS
2008年第5期77-80,共4页
Baosteel Technology
关键词
扫描线
缺陷分割
带钢
低对比度
scan line
defect segmentation
steel strip
low contrast
