Multi-mode optical fiber

Speckle pattern

Image (mathematics)

Optics

Physics

Pattern recognition (psychology)

Artificial intelligence

Composite material

Materials science

Optical fiber

Computer vision

Computer science

Artificial neural network

Fiber

Telecommunications

Intensity (physics)

Optica

We use Deep Neural Networks (DNNs) to classify and reconstruct a large database of handwritten digits from the intensity of the speckle patterns that result after the images propagated through multimode fibers (MMF). Images transmitted through fibers with up to 1km length were recovered. The ability of the network to recognize the input degraded with fiber length but the performance could be enhanced if the neural networks were trained to first reconstruct the image and then classify it rather than classify it directly from the speckle intensity.

Learning to see through multimode fibers