Hyperspectral Reconstruction of Skin Through Fusion of Scattering Transform Features
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929315250176000 |
|---|---|
| author | Czaja, Wojciech Emidih, Jeremiah Kolstoe, Brandon Spencer, Richard G. |
| author_facet | Czaja, Wojciech Emidih, Jeremiah Kolstoe, Brandon Spencer, Richard G. |
| contents | Hyperspectral imagery (HSI) is an established technique with an array of applications, but its use is limited due to both practical and technical issues associated with spectral devices. The goal of the ICASSP 2024 'Hyper-Skin' Challenge is to extract skin HSI from matching RGB images and an infrared band. To address this problem we propose a model using features of the scattering transform - a type of convolutional neural network with predefined filters. Our model matches and inverts those features, rather than the pixel values, reducing the complexity of matching while grouping similar features together, resulting in an improved learning process. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_10030 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Hyperspectral Reconstruction of Skin Through Fusion of Scattering Transform Features Czaja, Wojciech Emidih, Jeremiah Kolstoe, Brandon Spencer, Richard G. Image and Video Processing Machine Learning Hyperspectral imagery (HSI) is an established technique with an array of applications, but its use is limited due to both practical and technical issues associated with spectral devices. The goal of the ICASSP 2024 'Hyper-Skin' Challenge is to extract skin HSI from matching RGB images and an infrared band. To address this problem we propose a model using features of the scattering transform - a type of convolutional neural network with predefined filters. Our model matches and inverts those features, rather than the pixel values, reducing the complexity of matching while grouping similar features together, resulting in an improved learning process. |
| title | Hyperspectral Reconstruction of Skin Through Fusion of Scattering Transform Features |
| topic | Image and Video Processing Machine Learning |
| url | https://arxiv.org/abs/2404.10030 |