Accurate Tools for Analyzing the Behavior of Impulse Noise Reduction Filters in Color Images

Abstract

Effective cancellation of noise and preservation of color/structural information are features of paramount importance for any filter devoted to impulse noise removal in color images. In this paper novel full-reference tools for analyzing the behavior of this family of filters are presented. The proposed approach is based on the classification of color errors into two main classes that separately take into account the inaccuracy in removing noise pulses and the filtering distortion. The distortion errors are then classified into two subclasses for a deeper analysis of the filtering behavior. Computer simulations show that the proposed method gives more accurate results than using other measures of filtering performance in the literature. Furthermore, the method can easily yield the spatial location of the different filtering features in the image.

Performance Evaluation of Noise Reduction Filters for Color Images through Normalized Color Difference (NCD) Decomposition

“…In this first experiment we briefly highlight the advantages of our method over the classical MSE and MAE evaluations (an in-depth analysis of the inaccuracy of MAE and MSE is reported in [21]. We generated two images having very different combinations of residual noise and edge preservation, as in [21]. We adopted vector median filters having different window sizes to produce these results.…”

“…They have limited accuracy in estimating the different filtering features. As already observed for grayscale [20] and color images [21], MSE and MAE cannot accurately measure noise removal and detail preservation, because they cannot separate these features. Although the MAE is more sensitive to distortion than the MSE, it also depends upon the residual noise.…”