Image editing with spatiogram transfer

Abstract : Histogram equalization is a well known method for image contrast enhancement. Nevertheless, as histograms do not include any information on the spatial repartition of colors, their application to local image editing problems remains limited. To cope with this lack of spatial information, spatiograms have recently been proposed for tracking purposes. A spatiogram is an image descriptor that combines a histogram with the mean and variance of the position of each color. In this paper we address the problem of local retouching of images by proposing a variational method for spatiogram transfer. More precisely, a reference spatiogram is used to modify the color value of a given region of interest of the processed image. Experiments on shadow removal and inpainting demonstrate the strength of the proposed approach.
Liste complète des métadonnées
Contributor : Nicolas Papadakis <>
Submitted on : Thursday, March 1, 2012 - 4:59:31 PM
Last modification on : Wednesday, May 30, 2018 - 11:50:16 AM



Nicolas Papadakis, Aurélie Bugeau, Vicent Caselles. Image editing with spatiogram transfer. IEEE Transactions on Image Processing, Institute of Electrical and Electronics Engineers, 2012, 21 (5), pp.2513 - 2522. ⟨10.1109/TIP.2012.2183144⟩. ⟨hal-00675686⟩



Record views