Graph and Rank Regularized Matrix Recovery for Snapshot Spectral Image Demosaicing
| Autor: | Bert Geelen, Murali Jayapala, Grigorios Tsagkatakis, Panagiotis Tsakalides, Maarten Bloemen |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
medicine.medical_specialty
Demosaicing Matrix completion Pixel Computer science business.industry Hyperspectral imaging 020206 networking & telecommunications Pattern recognition 02 engineering and technology Spectral bands Convolutional neural network Computer Science Applications Spectral imaging Computational Mathematics Signal Processing 0202 electrical engineering electronic engineering information engineering medicine 020201 artificial intelligence & image processing Artificial intelligence business Image resolution |
| DOI: | 10.5281/zenodo.1454088 |
| Popis: | Snapshot Spectral Imaging (SSI) is a cutting-edgetechnology for enabling the efficient acquisition of the spatiospectralcontent of dynamic scenes using miniaturized platforms.To achieve this goal, SSI architectures associate each spatialpixel with a specific spectral band, thus introducing a criticaltrade-off between spatial and spectral resolution. In this paper,we propose a computational approach for the recovery of highspatial and spectral resolution content from a single or a smallnumber of exposures. We formulate the problem in a novelframework of spectral measurement matrix completion and wedevelop an efficient low-rank and graph regularized methodfor SSI demosaicing. Furthermore, we extend state-of-the-artapproaches by considering more realistic sampling paradigmsthat incorporate information related to the spectral profileassociated with each pixel. In addition to reconstruction quality, we also investigate the impact of recovery on subsequent analysistasks like classification using state-of-the-art convolutional neural networks. We experimentally validate the merits of the proposedrecovery scheme using synthetically generated data from indoor and satellite observations and real data obtained with an IMECvisible range SSI camera. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|