Algorithms of Three-Dimensional Filtration Using the Fuzzy-Set Theory for Color Image Sequences Degraded by Noise

摘要

The proposed algorithms use the values of multichannel pixels and angular differences between them for jointly filtering neighboring images on the basis of new fuzzy-logic rules, which make it possible to select pixels of similar structure, thus significantly increasing the processed sample volume and improving the filtration quality. Criteria used in describing and comparing the known and proposed algorithms are the peak signal-to-noise ratio (PSNR) in decibels, the me^n absolute error (MAE) determining the quality of reconstruction of fine details in the image, and also the chromatic parameters such as, for example, the normalized chromatic difference (NCD) and the mean chromatic ratio error (MCRE) [6-8].