Smoothed Shock Filtering: Algorithm and Applications

This article presents the smoothed shock filter, which iteratively produces local segmentations in image’s inflection zones with morphological operators (dilations, erosions). Hence, it enhances contours by creating ruptures, while preserving homogeneous regions. After describing algorithm, we show that is a robust approach for denoising, compared to related works. Then, expose how exploited this filter as pre-processing step different image analysis tasks (medical segmentation, fMRI, and texture classification). By means of its ability enhance important patterns images, has real positive impact upon such applications, would like explore more future.