Prediction of line-and-space pattern after etching based on scanning electron microscope image of corresponding resist pattern using machine learning

Yuqing Jin; Takahiro Kozawa

doi:10.1117/12.2614161

25 May 2022 Prediction of line-and-space pattern after etching based on scanning electron microscope image of corresponding resist pattern using machine learning

Yuqing Jin, Takahiro Kozawa

Author Affiliations +

Proceedings Volume 12055, Advances in Patterning Materials and Processes XXXIX; 120550T (2022) https://doi.org/10.1117/12.2614161
Event: SPIE Advanced Lithography + Patterning, 2022, San Jose, California, United States

Conference Poster

Abstract

Scanning electron microscopy (SEM) image is an indispensable device in inspection of photoresist and etched Si patterns. On the other hand, extreme ultraviolet (EUV) radiation offers high resolution in lithography fabrication. Owing to the application of EUV, the feature size of photomask produced by electron beam (EB) lithography is reduced as well. The reduction of feature size made the information extraction from SEM image difficult due to the technical limitation. This proceeding reports a strategy to extract the information of line-and-space pattern. The main step classification of line, space and edge class was realized by unsupervised machine learning – hierarchical clustering. Hierarchical clustering can integrate the brightness and coordination information in classification, and thus the classification ability of it is better than image thresholding. Furthermore, the classification result was used in prediction for etching pattern. The precision and recall of prediction were verified by confusion matrix.

Conference Presentation

Citation Download Citation

Yuqing Jin and Takahiro Kozawa "Prediction of line-and-space pattern after etching based on scanning electron microscope image of corresponding resist pattern using machine learning", Proc. SPIE 12055, Advances in Patterning Materials and Processes XXXIX, 120550T (25 May 2022); https://doi.org/10.1117/12.2614161

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available