Deep learning-based multimode fiber imaging in multispectral and multipolarimetric channels

Multimode optical fiber (MMF) imaging is an emerging fiber imaging technology that has been developed during the last decade. In this work, we demonstrate deep-learning-based MMF imaging for multispectral and multipo-larimetric channels. Specifically, by controlling the wavelength and polarization of the incident light of MMF, different spectral and polarization channels are constructed. We conduct MMF transmissive imaging experiments and record a large number of object-speckle pairs in each channel for neural network training. A neural net-work is trained to simultaneously reconstruct the intensity and classify the channel of objects in eight spectral or nine polarimetric channels. The average structural similarity (SSIM) of the image reconstruction in each spec-tral and polarimetric channel exceeded 0.9 with the accuracy of the channel classification exceeding 99.9%. By superimposing speckle patterns of different spectral channels, a new dataset is constructed for training, and the reconstruction of images containing multiwavelength information is also tested in eight spectral channels. Our findings have the potential to extend the application of MMF imaging with spectral and polarimetric information

Automated summary

Multimode optical fiber (MMF) imaging is an emerging technology that allows for multispectral and polarimetric imaging. By controlling the wavelength and polarization, different channels can be constructed. With neural network training, image reconstruction and channel classification can be achieved with high accuracy and similarity.