Automated spectral decomposition and reconstruction of optical properties using a mixed autoencoder approach
The presented ANN is a viable tool for extracting the spectral behavior of absorbers and scatterers without the need for prior knowledge of these components in the test and training data. Potential future applications could include the extraction of relative concentrations of constituents in tissue.
Authors
- Walter Blondel (ORCID: https://orcid.org/0000-0001-5866-7228)
- Martin Hohmann (ORCID: https://orcid.org/0000-0001-5099-1015)
- Dongqin Ni (ORCID: https://orcid.org/0000-0003-2533-8932)
- Marine Amouroux (ORCID: https://orcid.org/0000-0001-7235-4447)
Institutions
- Centre National de la Recherche Scientifique (FR)
- Friedrich-Alexander-Universität Erlangen-Nürnberg (DE)
- Centre de Recherche en Automatique de Nancy (FR)
- Université de Lorraine (FR)
Publication Details
- Journal
- Journal of Biomedical Optics
- Published
- 2025-04-09
- DOI
- https://doi.org/10.1117/1.jbo.30.4.047001
- Primary Topic
- Industrial Vision Systems and Defect Detection
- Type
- article
- Field-Weighted Citation Impact
- 0.00