Automating microscopic image analysis post-photolithography with machine learning

This thesis addresses the challenges in the manual analysis of semiconductor images by leveraging machine learning techniques to automate the process, with a focus on the photolithography stage. We compare various machine learning techniques for classifying images based on exposure and development levels, aimed at overcoming the limitations of human error in traditional analysis methods. In this thesis, we have created a dataset and used a comprehensive framework for the application of machine learning models. By shifting the focus from merely detecting surface defects to understanding the underlying causes during the photolithography process, this research aims to provide more targeted solutions for improving semiconductor manufacturing and understanding the errors. The findings of this thesis have the potential to enhance methodological precision and efficiency in semiconductor research, particularly beneficial in academic settings for instant analysis and feedback, thereby improving the learning experience for students studying this critical phase of semiconductor manufacturing.

Name thesis:degree_name

M.S.

Level thesis:degree_level

Thesis

Discipline thesis:degree_discipline

Computer Science

Grantor

University of Illinois at Urbana-Champaign

Year dc:date

2024

Author dc:creator

• Fulfagar, Hardik Sandeep

Contributors dc:contributor

• Nahrstedt, Klara

• Machine Learning
• Computer Vision
• Semiconductor Photolithography
• Microscopic Image Analysis Automation
• Dataset Creation
• Image Classification
• Semiconductor Defect Detection

Statement dc:rights

• Copyright 2024 Hardik Sandeep Fulfagar

Language dc:language

en, eng

Handle dc:identifier

https://hdl.handle.net/2142/124402

OAI record oai:identifier

https://www.ideals.illinois.edu/oai-pmh?verb=GetRecord&metadataPrefix=etdms&identifier=oai%3Awww.ideals.illinois.edu%3A2142%2F124402