Home – Home – Jornals – Avtometriya 2007 number 6

The problem of image reconstruction is considered for the case when the right-hand side of the 2D integral equation and the point-spread function (the integral equation kernel) are given with random errors. A stable image reconstruction algorithm is proposed. It is a combination of a regularizing algorithm for solving an integral equation (frequency filtering) and a local nonlinear filter (spatial filtering). Characteristics of the 2D point-spread function of the regularizing algorithm are introduced. The regularization parameter is chosen according to the required regularizing algorithm resolution. For eliminating the random reconstruction error, the regularized solution is subjected to nonlinear local filtering that preserves high-frequency information components of the image.