Deep Learning Hybrid Architecture Based on Vision Transformer for Phase Analysis of Moiré Fringes

Overlay accuracy is a fundamental indicator of a photolithography machine performance. Misalignment between the mask and wafer is the main factor affecting overlay accuracy. The photolithographic alignment method, which uses Moiré fringes, is notable for its straightforward optical path a...

Full description

Saved in:
Bibliographic Details
Main Authors: Dajie Yu, Junbo Liu, Chuan Jin, Yuyang Li, Kairui Zhang, Ji Zhou
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Photonics Journal
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10970258/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849736530513362944
author Dajie Yu
Junbo Liu
Chuan Jin
Yuyang Li
Kairui Zhang
Ji Zhou
author_facet Dajie Yu
Junbo Liu
Chuan Jin
Yuyang Li
Kairui Zhang
Ji Zhou
author_sort Dajie Yu
collection DOAJ
description Overlay accuracy is a fundamental indicator of a photolithography machine performance. Misalignment between the mask and wafer is the main factor affecting overlay accuracy. The photolithographic alignment method, which uses Moiré fringes, is notable for its straightforward optical path and high precision. However, the alignment accuracy is significantly influenced by the Moiré fringe phase analysis algorithm. This paper proposes a hybrid deep learning architecture based on a Vision Transformer for Moiré fringe phase analysis. By training on various types of Moiré fringe datasets, the model can predict the fringe wrapping phase, allowing for the analysis of elements within the wrapping phase, including displacement information. This method combines the multi-head attention mechanism of a Vision Transformer with deep learning feature extraction to build a hybrid deep learning architecture. This model effectively learns the mathematical mapping between the Moiré fringe phase information and actual offset, accurately outputting true Moiré fringe phase data. Results show that despite the presence of Gaussian noise and tilted states, the hybrid architecture maintains a Root Mean Square Error (RMSE) within the range of 6–7 nm, and a Structural Similarity Index (SSIM) above 0.70, and Peak Signal-to-Noise Ratio (PSNR) is consistently maintained above 36. Consequently, the proposed model demonstrates superior robustness in handling noisy data compared to existing phase retrieval techniques. Additionally, the model has been optimized in structure to more efficiently extract phase information from complex Moiré fringe patterns. This study offers valuable insights for expanding Moiré fringe imaging applications.
format Article
id doaj-art-4e236a15028b4adaa4d0e202c33075e7
institution DOAJ
issn 1943-0655
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Photonics Journal
spelling doaj-art-4e236a15028b4adaa4d0e202c33075e72025-08-20T03:07:14ZengIEEEIEEE Photonics Journal1943-06552025-01-011731810.1109/JPHOT.2025.356254210970258Deep Learning Hybrid Architecture Based on Vision Transformer for Phase Analysis of Moiré FringesDajie Yu0https://orcid.org/0009-0002-3356-6847Junbo Liu1https://orcid.org/0000-0002-1447-7606Chuan Jin2Yuyang Li3Kairui Zhang4Ji Zhou5https://orcid.org/0000-0001-8028-0134National Key Laboratory of Optical Field Manipulation Science and Technology, Chinese Academy of Science, Chengdu, Sichuan, ChinaNational Key Laboratory of Optical Field Manipulation Science and Technology, Chinese Academy of Science, Chengdu, Sichuan, ChinaNational Key Laboratory of Optical Field Manipulation Science and Technology, Chinese Academy of Science, Chengdu, Sichuan, ChinaNational Key Laboratory of Optical Field Manipulation Science and Technology, Chinese Academy of Science, Chengdu, Sichuan, ChinaNational Key Laboratory of Optical Field Manipulation Science and Technology, Chinese Academy of Science, Chengdu, Sichuan, ChinaNational Key Laboratory of Optical Field Manipulation Science and Technology, Chinese Academy of Science, Chengdu, Sichuan, ChinaOverlay accuracy is a fundamental indicator of a photolithography machine performance. Misalignment between the mask and wafer is the main factor affecting overlay accuracy. The photolithographic alignment method, which uses Moiré fringes, is notable for its straightforward optical path and high precision. However, the alignment accuracy is significantly influenced by the Moiré fringe phase analysis algorithm. This paper proposes a hybrid deep learning architecture based on a Vision Transformer for Moiré fringe phase analysis. By training on various types of Moiré fringe datasets, the model can predict the fringe wrapping phase, allowing for the analysis of elements within the wrapping phase, including displacement information. This method combines the multi-head attention mechanism of a Vision Transformer with deep learning feature extraction to build a hybrid deep learning architecture. This model effectively learns the mathematical mapping between the Moiré fringe phase information and actual offset, accurately outputting true Moiré fringe phase data. Results show that despite the presence of Gaussian noise and tilted states, the hybrid architecture maintains a Root Mean Square Error (RMSE) within the range of 6–7 nm, and a Structural Similarity Index (SSIM) above 0.70, and Peak Signal-to-Noise Ratio (PSNR) is consistently maintained above 36. Consequently, the proposed model demonstrates superior robustness in handling noisy data compared to existing phase retrieval techniques. Additionally, the model has been optimized in structure to more efficiently extract phase information from complex Moiré fringe patterns. This study offers valuable insights for expanding Moiré fringe imaging applications.https://ieeexplore.ieee.org/document/10970258/Deep learninghybrid architecturephase analysisMoiré fringes
spellingShingle Dajie Yu
Junbo Liu
Chuan Jin
Yuyang Li
Kairui Zhang
Ji Zhou
Deep Learning Hybrid Architecture Based on Vision Transformer for Phase Analysis of Moiré Fringes
IEEE Photonics Journal
Deep learning
hybrid architecture
phase analysis
Moiré fringes
title Deep Learning Hybrid Architecture Based on Vision Transformer for Phase Analysis of Moiré Fringes
title_full Deep Learning Hybrid Architecture Based on Vision Transformer for Phase Analysis of Moiré Fringes
title_fullStr Deep Learning Hybrid Architecture Based on Vision Transformer for Phase Analysis of Moiré Fringes
title_full_unstemmed Deep Learning Hybrid Architecture Based on Vision Transformer for Phase Analysis of Moiré Fringes
title_short Deep Learning Hybrid Architecture Based on Vision Transformer for Phase Analysis of Moiré Fringes
title_sort deep learning hybrid architecture based on vision transformer for phase analysis of moir x00e9 fringes
topic Deep learning
hybrid architecture
phase analysis
Moiré fringes
url https://ieeexplore.ieee.org/document/10970258/
work_keys_str_mv AT dajieyu deeplearninghybridarchitecturebasedonvisiontransformerforphaseanalysisofmoirx00e9fringes
AT junboliu deeplearninghybridarchitecturebasedonvisiontransformerforphaseanalysisofmoirx00e9fringes
AT chuanjin deeplearninghybridarchitecturebasedonvisiontransformerforphaseanalysisofmoirx00e9fringes
AT yuyangli deeplearninghybridarchitecturebasedonvisiontransformerforphaseanalysisofmoirx00e9fringes
AT kairuizhang deeplearninghybridarchitecturebasedonvisiontransformerforphaseanalysisofmoirx00e9fringes
AT jizhou deeplearninghybridarchitecturebasedonvisiontransformerforphaseanalysisofmoirx00e9fringes