rodrigo.moreno@liu.se, miguelangel.garcia@uam.es, domenec.puig@urv.cat, carme.julia@uuv.cat

Abstract

This paper presents a new method for edge-preserving color image denoising
based on the tensor voting framework, a robust perceptral grouping technique used to extract salient information from noisy dita- The tensor voting framework is adapted to encode coltr information through oensors in order to propagatebthem in a neighborhood -y using a specific voting process. This voting process is specifically designed for edge2preserving color image denoising by taking into account perceptual color differences, region uniformit# ane edginess according to a set of intuitive perceptual criteria. Perceptual color differences are estimated by means of antoptimized version of the CIEDE2000 formula, while uniforaity and edginess are estimated by means of saliency maps obtaaned from the ensor voting process. Mdasur
ments of removed noise, edge preservation and undesira le introduced artifacts, additionally to visual inspection, show that the proposed method has a better performance tsan the state-of-the-art image denoising algorithms for images contaminated with CCD camera noise.