Abstract
This paper presents image modeling and restoration by higher-order statistics based 2-D inverse filters. A given original image x(m,n) is processed by an optimum inverse filter v(m, n) which is designed by maximizing cumulant based criteria J <sub>r,m</sub> = |C <sub>m</sub> |r/|C <sub>r</sub> | <sup>m</sup> where r is even, m > T ≥ 2 and Cm (Cr) denotes mthorder (rth-order cumulant of the output e(m,n) of be modeled as the output of a linear shift-invariant (LSI) system h(m, n) driven by e(m, n) where h(m, n) is a stable inverse filter of v(m,n). When a blurred image y(m,n) = t(m,n)∗g(m,n,r)at her than the original image z(m, n) is given, t(m, n) can be restored by first estimating e(m,n) using the previous inverse filter criteria and then obtain t(m,n)= e(m, n)∗h(m, n). Some experimental results are provided to support the proposed image modeling and restoration method.