| アイテムタイプ |
学術雑誌論文 / Journal Article(1) |
| 公開日 |
2024-08-06 |
| タイトル |
|
|
タイトル |
Unsupervised learning with a physics-based autoencoder for estimating the thickness and mixing ratio of pigments |
| 言語 |
|
|
言語 |
eng |
| 資源タイプ |
|
|
資源タイプ |
journal article |
| アクセス権 |
|
|
アクセス権 |
open access |
| 著者 |
Shitomi, Ryuta
Tsuji, Mayuka
藤村, 友貴
舩冨, 卓哉
向川, 康博
Morimoto, Tetsuro
Oishi, Takeshi
Takamatsu, Jun
Ikeuchi, Katsushi
|
| 抄録 |
|
|
内容記述タイプ |
Abstract |
|
内容記述 |
Layered surface objects represented by decorated tomb murals and watercolors are in danger of deterioration and damage. To address these dangers, it is necessary to analyze the pigments’ thickness and mixing ratio and record the current status. This paper proposes an unsupervised autoencoder model for thickness and mixing ratio estimation. The input of our autoencoder is spectral data of layered surface objects. Our autoencoder is unique, to our knowledge, in that the decoder part uses a physical model, the Kubelka$2013Munk model. Since we use the Kubelka$2013Munk model for the decoder, latent variables in the middle layer can be interpretable as the pigment thickness and mixing ratio. We conducted a quantitative evaluation using synthetic data and confirmed that our autoencoder provides a highly accurate estimation. We measured an object with layered surface pigments for qualitative evaluation and confirmed that our method is valid in an actual environment. We also present the superiority of our unsupervised autoencoder over supervised learning. |
| 書誌情報 |
en : Journal of the Optical Society of America A
巻 40,
号 1,
p. 116-128,
発行日 2022-12-19
|
| 出版者 |
|
|
出版者 |
Optica Publishing Group |
| ISSN |
|
|
収録物識別子タイプ |
EISSN |
|
収録物識別子 |
1520-8532 |
| 出版者版DOI |
|
|
関連タイプ |
isReplacedBy |
|
|
識別子タイプ |
DOI |
|
|
関連識別子 |
https://doi.org/10.1364/JOSAA.472775 |
| 出版者版URI |
|
|
関連タイプ |
isReplacedBy |
|
|
識別子タイプ |
URI |
|
|
関連識別子 |
https://opg.optica.org/josaa/fulltext.cfm?uri=josaa-40-1-116&id=524419 |
| 権利 |
|
|
権利情報 |
$00A9 2022 Optica Publishing Group. Users may use, reuse, and build upon the article, or use the article for text or data mining, so long as such uses are for non-commercial purposes and appropriate attribution is maintained. All other rights are reserved. |
| 著者版フラグ |
|
|
出版タイプ |
NA |
