BBP-assisted defect detection process for SEM image

Abstract

The rendered image is aligned with a scanning electron microscope (SEM) image to produce an aligned rendered image. A reference image is aligned with the SEM image to produce an aligned reference image. A threshold probability map is also generated. Dynamic compensation of the SEM image and the aligned reference image may result in a corrected SEM image and a corrected reference image. A threshold defect map may be generated and defects of the threshold probability map and signal-to-noise ratio defects of the threshold defect map may be filtered using broadband plasma-based properties to produce a cluster of defects of interest.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS [0002] This application claims priority to US Provisional Application No. 62 / 928,513, filed October 31, 2019, the entire disclosure of which is hereby incorporated by reference. technical field [0003] The present disclosure generally relates to semiconductor defect detection and classification. Background technique [0004] The evolution of the semiconductor manufacturing industry places higher demands on yield management and especially on metrology and inspection systems. Critical dimensions continue to shrink, and the industry needs to reduce the time it takes to achieve high-yield, high-value production. Minimizing the total time from detection of a yield issue to resolution of said issue determines ROI for semiconductor manufacturers. [0005] An inspection algorithm implemented in a scanning electron microscope (SEM) tool uniquely uses deep learning (DL) to detect defects of interest (DOIs). During training, the use...

AI Technical Summary

Problems solved by technology

Aligning the rendered image with the SEM image to generate an aligned rendered image

Images