PSF estimation and image restoration for noiseless motion blurred images

In this paper we consider the restoration problem of noiseless linear motion bluffed image. The success of restoring this kind of blurred image highly depends on precise estimation of parameters of point spread function (PSF), i.e., motion length and motion direction. In this paper a novel idea for PSF parameters estimation and new approach for motion bluffed image restoration are discussed. In motion length estimation, we apply 2-D cepstral analysis used to find periodicity of sinc function whose structure remains in the spectrum of bluffed image. In motion direction estimation, we use our proposed, modified discrete Radon transform and 2-D cepstral analysis. The value of estimated length is used as a criteria of which one of the two methods can give better result for a certain length. The estimated PSF parameters are then used in the image restoration. To restore the bluffed image, we work in spatial domain by inverting the lower triangular matrix that expresses the degradation process. Finally, test results of our method showed good reproduction of the original image.