2024/04/15 by Wojciech Czaja, Czaja, Wojciech, Jeremiah Emidih +5
Chemistry · Engineering · Medicine · #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Video Processing (eess.IV) #Machine Learning (cs.LG) #Optical Imaging and Spectroscopy Techniques #Optical Polarization and Ellipsometry #Spectroscopy and Chemometric Analyses #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2404.10030
openalex publication_date 2024/04/15 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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.