Recurrent neural network application to image filtering: 2-D Kalman filtering approach
Roman W. Świniarski, Andrzej Dzieliński, Sławomir Skoneczny, Michael P. Butler · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 1991
A Kalman filter for a class of 2D image state-space model is presented. Kalman filter equations are derived for the reduced version of 2D system model and resulting state estimate is expressed in terms of original 2D system. A neural network computing the Kalman filter gain has been designed. This way burdensome Riccati equation solution was improved. The evaluated Kalman filter gain is used to estimate the real input noisy image. As a result a restore image is obtained.