Machine Learning Improves Fibre Image Transmission

Created August 15, 2018
Applications and Research

Researchers at the Ecole Polytechnique Fédérale de Lausanne (EPFL) have taught a type of machine learning algorithm to reconstruct images that became blurred while being transmitted through an optical fibre. The work could increase the amount of information transmitted through telecommunications networks, improve endoscopic imaging used in medical diagnosis and enhance the capacity and quality of optical fibres.

“We use modern deep neural network architectures to retrieve the input images from the scrambled output of the fibre,” said Demetri Psaltis, the head of EPFL’s Optics Laboratory, who led the research in collaboration with colleague Christophe Moser from the Laboratory of Applied Photonics Devices. “We demonstrate that this is possible even for fibres 1 km long,” he added, calling the work an important milestone. Their research has now been published in the journal Optica.

The EPFL researchers note that while multimode fibres are well suited for carrying light-based signals, they have not successfully been used to transmit images over long distances before. This is because images travel through all the channels, and what emerges at the other end is a pattern of speckles that the human eye cannot decode.

To tackle this problem, Dr. Psaltis and his team turned to a deep neural network, the type of machine-learning algorithm that can give computers the ability to identify objects in photographs. The design of these algorithms is inspired by the way neurons transmit information in the human brain. Input is processed through several “hidden layers” of artificial neurons, each of which performs a small calculation and passes the result on to neurons in the next layer.

Our brains develop mental models for objects by being exposed to many different examples, so that, for example, when encountering a new type of tree we are able to recognise it as a tree instead of a telephone pole or a bush. Similarly, when a deep neural network is exposed to a large enough set of training data, the machine learns to identify the input by recognising the associated patterns of output.

Navid Borhani, a scientist who participated in the research, says this machine learning method is much simpler than other approaches to reconstructing images that have been transmitted through optical fibres, which require making a holographic measurement of the output. The deep neural network was able to cope with distortions caused by environmental disturbances as the signal passed through the fibre. Random fluctuations in temperature along the length of the fibre together with movements caused by air currents can add noise to the image – and the noise worsens the farther the signal has to travel.

“The remarkable ability of deep neural networks to retrieve information transmitted through multimode fibres is expected to benefit medical procedures like endoscopy and communications applications,” according to Dr. Psaltis. Telecommunication signals often have to travel through many km of fibre and can suffer distortions, which this method could correct. Doctors could use ultrathin fibre probes to collect images of the tracts and arteries inside the human body without needing complex holographic recorders or worrying about movement.

https://information.epfl.ch

Caption: A speckle pattern from an image transmitted through a multimode fibre passes through the hidden layers of a deep neural network and is reproduced as the number 3. / Demetri Psaltis, EPFL

avatar

This article was written
by John Williamson

John Williamson is a freelance telecommunications, IT and military communications journalist. He has also written for national and international media, and been a telecoms advisor to the World Bank.