For defect detection and defect classification problems of Scanning Electron Microscope( SEM) images during wafer inspection,this paper applies a Convolutional Neural Network( CNN) called ZFNet to classify wafer defects. On this basis,a patch-based CNN defect detection algorithm is proposed. For better accuracy and higher speed,another detection algorithm is proposed by modifying Faster RCNN classifier. Experimental results show that,by learning from the defects data marked with locations and types,the two ...
【基金】
国家自然科学基金(61474098,61674129)
【更新日期】
2018-08-22
【分类号】
TP391.41
【正文快照】
[2]0概述进行对比,取差异较大的区域作为缺陷,其关键在现代半导体制造过程中大量使用扫描电镜于如何得到准确的参考图像。传统的缺陷分类算法(Scanning Electron Microscope,SEM)对晶圆进行扫是基于缺陷区域提取特定特征,再由此设计分类器描从而成像,然后通过查找并分析扫描图?