Abstract
The pivoting problem encountered in regularized image restoration is how to evaluate the regularization parameter. Existing methods for evaluating this regularization parameter are categorized to two main groups; methods that require knowledge of the noise variance in the degraded image and methods that do not. This paper suggests a new approach for choosing the regularization parameter. It depends on maximizing the power in the restored image by the coincidence of the passband of the regularization filter with the frequency band in which most of the image power exists. The suggested method has an iterative nature and requires no a priori knowledge of the noise variance, which may be inexact. Results show that the estimated value of the regularization parameter coincides. with the minimum of the mean squared error and results in enhanced image restoration.