The algorithm of identification and restoration based on the priori blur models for the degraded images

In general practical applications, the point spread function (PSF) of the imaging system, the imaging process, and the observation noise, are unknown a priori information. Therefore, the identification of the PSF is a challenging and difficult problem in the world. The algorithm of identification of the PSF and the restoration of the blurred images based on the priori blur models (known as the PBM algorithm) is proposed. In practical application, the priori models of the PSF mainly consist of the linear motion blur, out of focus blur and the Gaussian blur. In the situation of that the degradation process is formed by the one of the above point spread functions, the PSF can be formulated in parametric model. The corresponding parameters of the model are determined by the algorithm proposed in this paper. Thus, the PSF is obtained according to the parameter of the model consequently. First, the parameter changing scope and the increment step length of the parameters are provided based on the original guess. Second, the criterion that the Euclid length of the difference between the observed image and blurred image corresponding to the PSF is minimized is incorporated in order to determine the parameter of the PSF. Therefore, the PSF is identified by the parametric model and the original image is estimated via the ordinary image restoration algorithms. In this paper, we applied the Wiener filter to restore the original images. The experimental results show that the identified result of the PSF is reliable and accurate and the restoration effect with the identified PSF is better when the observed image have high signal to noise ratio (SNR).