摘要
针对硅片表面缺陷的特点,对其缺陷的提取技术进行了研究,采用了多结构元素的广义形态闭-开和形态开-闭滤波器,结合改进分水岭算法进行缺陷提取.滤波器对输入图像及滤波后图像的梯度图像进行平滑,实现消除噪声、简化图像、保持细节的作用.为了克服分水岭的过度分割问题,提出了改进的分水岭算法,利用区域强度准则和边界强度准则对过分割区域进行合并,很好的解决了过分割问题.实验表明,该方法可以提取精确且封闭的缺陷边缘轮廓,为进一步的缺陷特征量的提取与选择奠定了基础.
Defect extraction techniques are studied regarding the silicon surface defect, generalized close-opening and open-closing filter based on the morphological filter with the different size structuring element, and improved watershed is used. The filter is introduced to eliminate the noise and simplify the image and morphological gradient image while pre- serving the details. In order to reduce the over-segmentation of the watershed algorithm, suggests an improved watershed, region average gray value and edge strength criterion is used in merging operation and has a good effect on segmentation. The experiments show that this method can provide accurately localized and closed region contours, which lays a good foundation for defect feature extraction and selection.
出处
《河北工业大学学报》
CAS
北大核心
2009年第6期44-48,共5页
Journal of Hebei University of Technology
关键词
图像处理
缺陷检测
形态滤波
分水岭
过分割
image processing
defects detection
morphological filter
watershed
over-segmentation