Presentation
1 August 2021 Interpretable deep learning for imaging through scattering medium
Author Affiliations +
Abstract
Imaging through scattering medium has wide applications across many areas. Here, we present a new deep learning framework for improving the robustness against physical perturbations of the scattering medium. The trained DNN can make high-quality predictions beyond the training range which is across 10X depth-of-field (DOF). We develop a new analysis framework based on dimensionality reduction for revealing the information contained in the speckle dataset, interpreting the mechanism of our DNN, and visualizing the generalizability of the DNN model. This allows us to further elucidate on the information encoded in both the raw speckle measurements and the working principle of our speckle-imaging deep learning model.
Conference Presentation
© (2021) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Yunzhe Li, Shiyi Cheng, Yujia Xue, and Lei Tian "Interpretable deep learning for imaging through scattering medium", Proc. SPIE 11804, Emerging Topics in Artificial Intelligence (ETAI) 2021, 118041O (1 August 2021); https://doi.org/10.1117/12.2594043
Advertisement
Advertisement
KEYWORDS
Light scattering

Diffusers

Scattering

Neural networks

Speckle

Speckle pattern

Glasses

Back to Top