Review-SEM image analysis with K-means algorithm: AM: Advanced metrology/DI: Defect inspection

With the continuous shrink of technology nodes, lithography becomes more and more challenging. At 20 nm node, double patterning technology (DPT) was the usual way of achieving the fine device structures. For sub-14nm nodes the patterning choices for IDM's lie between SAQP plus EUV block or an EUV based direct patterning approach. As with any new technology adoption, yield ramp at the beginning takes effort. Defect locations identified by optical inspection tools need to be reviewed by review-SEM's to understand exactly which feature is failing in the region flagged by the optical tool. The images grabbed by the review-SEM tool are used for classification but rarely for quantification. The goal of this paper is to see if the thousands of existing review-SEM images can be used for quantification and further analysis. More specifically we address the SEM quantification problem with connected component and K-means cluster analysis algorithms.