NOTICE: Due to a lapse in annual appropriations, most of this website is not being updated. Learn more.
Form submissions will still be accepted but will not receive responses at this time. Sections of this site for programs using non-appropriated funds (such as NVLAP) or those that are excepted from the shutdown (such as CHIPS and NVD) will continue to be updated.
An official website of the United States government
Here’s how you know
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
Secure .gov websites use HTTPS
A lock (
) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.
Applications of machine learning at the limits of form-dependent scattering for defect metrology
Published
Author(s)
Mark Alexander Henn, Hui Zhou, Richard M. Silver, Bryan M. Barnes
Abstract
Undetected patterning defects on semiconductor wafers can have severe consequences, both financially and technologically. Industry is challenged to find reliable and easy-to-implement methods for defect detection. In this paper we present robust machine learning techniques that can be applied to classify defect images. We demonstrate the basic principles of an algorithm that uses a convolutional neural network and discuss how such networks can be improved not only in their architecture but also tailored to the specific challenges of defect inspection through more specialized performance metrics. These advances may lead to more cost-efficient measurements by adjusting the decision threshold to optimize the number of wrongly classified no-defect images.
Proceedings Title
Metrology, Inspection, and Process Control for Microlithography XXXIII
, M.
, Zhou, H.
, Silver, R.
and Barnes, B.
(2019),
Applications of machine learning at the limits of form-dependent scattering for defect metrology, Metrology, Inspection, and Process Control for Microlithography XXXIII, San Jose, CA, [online], https://doi.org/10.1117/12.2517285
(Accessed October 2, 2025)