ADFE(adaptive decision feedback equalizer ) is derived from transverse equalizer. It uses decision output signal to form a delay line, through which parts of coefficients are added together and are returned to the output. It can compensate for channels with severe intersymbol interference which is like the blurred image. The blur on image can be regarded as perturbation of the pixels, so a kind of ADFE is applied to 2D image restoration. The Lee filter is adopted to reduce noise. There are two adaptive filers in this method, so the forward filter has more flexibility to select its coefficients and not inverse blur only. As a result, the noise enhancement will not happen. Additionally, the support of the object is confirmed by threshold. The experiment proves that this new algorithm is robust under high noises, and that it′s an effective algorithm.