一种黑片图像亚像素边缘检测方法

为了提高黑片图像边缘检测的精度,提出了利用亚像素边缘检测技术来检测黑片图像的边缘.针对Zernike矩的亚像素边缘检测算法存在计算量大和边缘定位精度低等不足,利用Sobel算子对图像进行像素级边缘提取,然后利用改进的Zernike矩算子来检测黑片图像的亚像素边缘,为了防止Sobel算子遗漏可能的亚像素点,增加了一个搜索算法来提高检测的精度.实验结果表明,该方法测量精度高,定位精确,能够应用于黑片的在线检测.

A Silicon Sheet Steel Image Sub-pixel Edge Measurement Method

In order to improve the accuracy of Silicon sheet steel edge location,a sub-pixel edge detection method is presented in this paper.With the consideration that the Zernike moments has some limitation,such as the large amount of calculation and extracted wider edge than that of the original image,an improved method is proposed.Sobel operator is used to calculate the gray-level gradient image and locate one pixel accuracy,then the sub-pixel positioning algorithm of Zernike moments operator is used to calculate locations of object edges.In order to prevent the possible omission of sub-pixel,a search method is used to raise the detection accuracy.The experimental results show that this method has high accuracy,which positioning accuracy,which can be applied to the Silicon sheet steel inspection.