# Deep learning framework for analyzing birefringence imaging by incorporating optical polarization overlap in stress-induced ferroelectric SrTiO

https://mdr.nims.go.jp/datasets/5bb67fa0-d350-4b55-8f7d-ae82ca789338

## File

- [Deep learning framework for analyzing birefringence imaging by incorporating optical polarization overlap in stress-induced ferroelectric SrTiO.pdf](https://mdr.nims.go.jp/filesets/b34fa037-4df5-46b7-8d67-1ce73208527a/download) ([Detail](https://mdr.nims.go.jp/filesets/b34fa037-4df5-46b7-8d67-1ce73208527a.md))
- [Supplementary_Material.pdf](https://mdr.nims.go.jp/filesets/2e1b9be0-7982-4005-b9e7-7880fa23b430/download) ([Detail](https://mdr.nims.go.jp/filesets/2e1b9be0-7982-4005-b9e7-7880fa23b430.md))
- [TSTM-2025-2021_data.zip](https://mdr.nims.go.jp/filesets/363a6502-cccb-42a7-9c9a-05602a5bf5b8/download) ([Detail](https://mdr.nims.go.jp/filesets/363a6502-cccb-42a7-9c9a-05602a5bf5b8.md))

## Id

5bb67fa0-d350-4b55-8f7d-ae82ca789338

## Local identifier



## Visibility

open_to_public

## State

published

## Created at

2025-10-09T02:53:13.285367Z

## Updated at

2025-10-21T07:05:44.595646Z

## Published at

2025-10-21T06:43:17.457788Z

## Doi

https://doi.org/10.48505/nims.5801

## First published url

https://doi.org/10.1080/27660400.2025.2568376

## Date published

2025-12-31

## Recorded date published

2025-12-31

## Resource type

journal_article

## Manuscript type

accepted_manuscript

## Collection



## Title

- title: Deep learning framework for analyzing birefringence imaging by incorporating
    optical polarization overlap in stress-induced ferroelectric SrTiO
  title_type: original
  lang: en

## Description

- description: Optical microscopy is vital in many scientific fields, and various
    super-resolution techniques have been developed to overcome the resolution limit
    that restricts the separation of spatially mixed light. However, conventional
    methods inherently cannot resolve overlapping optical polarization (OP) components,
    limiting the ‘polarization resolution’ in polarized light microscopy. Instead
    of quantitatively evaluating ‘polarization resolution’, this study aims to reliably
    separate intrinsic OP states based on consistent clustering results that are robust
    to variations in the spatial receptive field (SRF) size. We integrate statistical
    analysis, machine learning, and deep learning to evaluate overlapping OP states
    in temperature-dependent birefringence imaging of the stress-induced ferroelectric
    SrTiO 3 under an external force of 231 MPa. A long short-term memory (LSTM) network
    is used to extract temperature-dependent features from sequential image data,
    which effectively captures subtle changes in structural and ferroelectric phase
    transitions. A 3D convolutional autoencoder (3DCAE) learns spatial relationships
    between adjacent pixels from these temperature-dependent features, addressing
    OP overlap at different spatial scales based on different SRF sizes. Although
    the 3DCAE output considerably depends on the SRF size, clustering results obtained
    via temperature series forest (Tsf) analysis are highly consistent. This robustness
    indicates that the extracted OP states reflect physically meaningful spatial distributions
    rather than convolution artifacts. The proposed sequential analytical framework
    successfully reconstructs intrinsic OP distributions while balancing local and
    global structural features, providing a robust foundation for OP-sensitive imaging
    in materials science.
  description_type: abstract
  lang: en

## Creator

- name: Hirotaka Manaka
  role: author
  organization: Kagoshima University
  department: a Graduate School of Science and Engineering
- name: Shoutarou Katayama
  role: author
- name: Soichiro Honda
  role: author
- name: Yoko Miura
  role: author

## Contact agent



## Publisher

organization: Taylor & Francis

## Managing organization



## Keyword

- subject: LSTM
  schema: not_defined
- subject: temperature series principal component analysis
  schema: not_defined
- subject: 3D convolutional autoencoder
  schema: not_defined
- subject: temperature series forest
  schema: not_defined
- subject: stress-induced ferroelectricity
  schema: not_defined
- subject: SrTiO3
  schema: not_defined

## Rights

- identifier: https://creativecommons.org/licenses/by/4.0/

## Other identifier(s)



## Data origin

- data_origin_type: other

## Embargo



## Journal

- title: Science and Technology of Advanced Materials
  issn: '27660400'
  volume: '5'
  article_number: '2568376'

## Conference



## Related item



## Funding



## Instrument



## Instrument operator



## Instrument managing organization



## Measurement method



## Specimen



## Chemical composition



## Structure for specimen



## Structural feature for specimen



## Specific property for specimen



## Process for specimen treatment



## Computational method



## Energy level/transition state



## Software



## Custom property



## Fileset

- id: b34fa037-4df5-46b7-8d67-1ce73208527a
  filename: Deep learning framework for analyzing birefringence imaging by incorporating
    optical polarization overlap in stress-induced ferroelectric SrTiO.pdf
  content_type: application/pdf
  size: 7222502
  md5: 6d72fb252399a96d6ec1080a50c81f60
- id: 2e1b9be0-7982-4005-b9e7-7880fa23b430
  filename: Supplementary_Material.pdf
  content_type: application/pdf
  size: 40491984
  md5: 386195f3748d634c009f4a1647bf20ca
- id: 363a6502-cccb-42a7-9c9a-05602a5bf5b8
  filename: TSTM-2025-2021_data.zip
  content_type: application/zip
  size: 908050
  md5: 21116367b9f6fd06c89bf1dce6108ece

## Thumbnail

fileset_id: b34fa037-4df5-46b7-8d67-1ce73208527a
filename: Deep learning framework for analyzing birefringence imaging by incorporating
  optical polarization overlap in stress-induced ferroelectric SrTiO.pdf