Unsupervised Image-to-Image Translation from MRI-based Simulated Images to Realistic Images Reflecting Specific Color Characteristics

Naoya Wada, Masaya Kobayashi

2022

Abstract

In this paper, a new domain adaptation technique is presented for image-to-image translation into the real-world color domain. Although CycleGAN has become a standard technique for image translation without pairing images to train the network, it is not able to adapt the domain of the generated image to small domains such as color and illumination. Other techniques require large datasets for training. In our technique, two source images are introduced: one for image translation and another for color adaptation. Color adaptation is realized by introducing color histograms to the two generators in CycleGAN and estimating losses for color. Experiments using simulated images based on the OsteoArthritis Initiative MRI dataset show promising results in terms of color difference and image comparisons.

Paper Citation

in Harvard Style

Wada N. and Kobayashi M. (2022). Unsupervised Image-to-Image Translation from MRI-based Simulated Images to Realistic Images Reflecting Specific Color Characteristics. In Proceedings of the 15th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2022) - Volume 2: BIOIMAGING; ISBN 978-989-758-552-4, SciTePress, pages 184-189. DOI: 10.5220/0010916300003123

in Bibtex Style

@conference{bioimaging22,
author={Naoya Wada and Masaya Kobayashi},
title={Unsupervised Image-to-Image Translation from MRI-based Simulated Images to Realistic Images Reflecting Specific Color Characteristics},
booktitle={Proceedings of the 15th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2022) - Volume 2: BIOIMAGING},
year={2022},
pages={184-189},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010916300003123},
isbn={978-989-758-552-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2022) - Volume 2: BIOIMAGING
TI - Unsupervised Image-to-Image Translation from MRI-based Simulated Images to Realistic Images Reflecting Specific Color Characteristics
SN - 978-989-758-552-4
AU - Wada N.
AU - Kobayashi M.
PY - 2022
SP - 184
EP - 189
DO - 10.5220/0010916300003123
PB - SciTePress