Neural network decision directed edge-adaptive Kalman filter

A neural network-based scheme for decision directed edge-adaptive Kalman filtering is introduced in this paper. A backpropagation neural network makes the decisions about the orientation of the edges based on the information in a window centered at the current pixel being processed. The appropriate image model is then chosen for the Kalman filter which closely snatches the local statistics of the image. This prevents the over-smoothing of the edges which will be caused by standard Kalman filter. Experimental results are presented which show the effectiveness of the proposed scheme