An adaptive model of bilateral filter is presented for digital in painting. The model works by transforming in painting into an equivalent energy condition minimization and generation of patches for missing areas by interpolating within working frame. It combines knowledge of local structure by bilateral filter and intensive value. Bilateral filter is adapted to missing regions to check similarity of regions to fill-in. Standard deviation in range kernel of the filter is regulated by total variation. This helps to create patches that keep edges. Total variation is also efficient for detection of missing pixels which possibly stay on edges. Benefit of the model was demonstrated in experiment of in painting for gray and color images.
Image-based estimation of skin lesions is efficient sub-field of medical imaging. The objective of task is to achieve more proper assessment of treatment effects. A significant group of skin lesion detection methods makes use of spatial relationships in order to deliver features for image region. Recently, a few study advances have been made in this particular group of area-based methods. This paper presents a new method that uses advantage of specific priori knowledge of lesion region detected by moment of patch. Since the lesion region determination basis is color values and surrounding pixels area moment of difference of two image patches predicts homologous changes as evaluation of similarity of the patches. We use an adequate algorithm to detect skin region with application of geometric moments. Our main contribution are (i) the exercising of area moment to compose a database of skin lesion templates, and (ii) a lesion region detection scheme that estimates the image patches resemblance based on moment of patches so that lesion region can be discovered. The capability of the method is demonstrated by analyzing images of a skin lesion benchmark using the templates extracted from other independent database.