Adaptative shock filter for image characters enhancement and denoising

The paper proposes an adaptive shock filter to restore noisy blurred image characters. This filter introduces an fuzzy decision mechanism to sharpen image features like edges and singularities while an anisotropic diffusion process is used to remove noise. A useful application of the proposed filter is the improvement of image segmentation and binarization task. Its efficiency on degraded document images is appropriately proven via a well-established experimental study based on a comparison with the state-of-the-art methods.