Motion blurred image deconvolution with anisotropic regularization

Image restoration or deconvolution is an evolving research topic in the area of image processing and computer vision. It refers to the task of recovering a good estimate of the true image from a degraded observation. In this paper, we consider the problem of restoring an image that has been blurred by a motion blur, which occurs in many practical applications. The anisotropic diffusion is used in the blind deconvolution process to regularize the solution. The key idea behind the anisotropic diffusion is to incorporate an adaptative smoothness constraint in the deconvolution process. That is, the smooth is encouraged in a homogeneous region and discourage across boundaries, in order to preserve the natural edge of the image. The estimation of the true image is solution to the Euler-Lagrange equation which is solved by an iterative scheme. The performance of this approach is then compared to some classical methods.