Deep Learning Enabled Real Time Speckle Recognition and Hyperspectral Imaging using a Multimode Fiber Array

Published on 2019-07-12T14:50:27Z (GMT) by
We demonstrate the use of deep learning for fast spectral deconstruction of speckle patterns. The artificial neural network can be effectively trained using numerically constructed multispectral datasets taken from a measured spectral transmission matrix. Optimized neural networks trained on these datasets achieve reliable reconstruction of both discrete and continuous spectra from a monochromatic camera image. Deep learning is compared to analytical inversion methods as well as to a compressive sensing algorithm and shows favourable characteristics both in the oversampling and in the sparse undersampling (compressive) regimes. The deep learning approach offers significant advantages in robustness to drift or noise and in reconstruction speed. In a proof-of-principle demonstrator we achieve real time recovery of hyperspectral information using a multi-core, multi-mode fiber array as a random scattering medium.

Cite this collection

Kurum, Ulas; Wiecha, Peter; French, Rebecca; Muskens, Otto (2019): Deep Learning Enabled Real Time Speckle Recognition and Hyperspectral Imaging using a Multimode Fiber Array. The Optical Society. Collection.

Thumbnail
La linea #3
2019-07-12T14:50:27Z
Thumbnail
La linea #4
2019-07-12T14:50:26Z
Thumbnail
La linea #2
2019-07-12T14:50:26Z
Thumbnail
Eclipse
2019-07-12T14:50:26Z
Thumbnail
La linea #1
2019-07-12T14:50:26Z