In plain words: A filter made from a reservoir network — fixed random connections that learn only at the output — is trained to reverse camera noise and distortion. It pulls clean images back out, and could be built right on the sensor.

Abstract · Reservoir Computing based Neural Image Filters

Clean images are an important requirement for machine vision systems to recognize visual features correctly. However, the environment, optics, electronics of the physical imaging systems can introduce extreme distortions and noise in the acquired images. In this work, we explore the use of reservoir computing, a dynamical neural network model inspired from biological systems, in creating dynamic image filtering systems that extracts signal from noise using inverse modeling. We discuss the possibility of implementing these networks in hardware close to the sensors.

Samiran Ganguly, Yunfei Gu, Yunkun Xie, Mircea R. Stan, Avik W. Ghosh, Nibir K. Dhar
arXiv:1809.02651 · cs.CV, cs.ET, cs.NE · submitted Sep 7, 2018
abstract · pdf · 5 pages, 4 figures, To appear in Conference Proceedings of The 44th Annual Conference of IEEE Industrial Electronics Society (2018): Special Session on Machine Vision, Control and Navigation