Title: IMPROVED BILATERAL FILTERING SCHEME FOR NOISE REMOVAL IN COLOR IMAGES

Year of Publication: Jun - 2012
Page Numbers: 118-130
Authors: Krystyna Malik, Bogdan Smolka
Conference Name: The International Conference on Informatics and Applications (ICIA2012)
- Malaysia

Abstract:


In this paper a new approach to the problem of noise removal in color images is presented. The proposed ltering design is a modi cation of the bilateral denos- ing scheme, which takes into account the similarity between color pixels and their spatial distance. How- ever, instead of direct calculation of the dissimilarity measure, the cost of a connection through a digital path joining the central pixel of the ltering window with the remaining pixels is determined. The lter output, like in the standard bilateral lter, is calcu- lated as a weighted average of the pixels surrounding the center of the ltering window, and the weights are functions of the minimal connection costs. Ex- perimental results prove that the introduced design yields signi cantly better results than the bilateral l- ter in the case of color images contaminated by strong mixed Gaussian and impulsive noise.