Abstract
This paper proposes a Kalman filter based robust restoration method with colored driving source for degraded images. This algorithm aims to achieve high quality image restoration for blur and noise disturbance from the canonical state space models with (i) a state equation composed of the original image, and (ii) an observation equation composed of the original image, blur, and noise. The remarkable feature of the proposed method is realization of high performance image restoration without sacrificing an original image despite simple image restoration using only Kalman filter. We show the effectiveness of the proposed method, which utilized the Kalman filter theory for the proposed canonical state space models with the colored driving source, using numerical results and subjective evaluation results.
