A Nonlinear Telegraph Equation for Edge-Preserving Image Restoration

Abstract

Poisson noise suppression is a challenging and important preprocessing stage for higher level image analysis. Therefore, in this paper, a new attempt has been made using telegraph equation and variational theory for Poisson noise suppression. The proposed approach enjoys the benefits of both telegraph-diffusion equation and Hessian edge detector, which is not only robust to noise but also preserves image structural details. The Hessian function has been used to distinguish between edges and noise. However, to the best of author’s knowledge, the Hessian edge detector driven telegraph-diffusion scheme has not been used before for Poisson noise suppression. With the proposed model, restoration is carried out on several natural images. The experimental results of proposed model are found better in terms of noise suppression and detail/edge preservation, with respect to the existing approaches.