Quantitative evaluation of detail-preserving and noise-removal abilities of morphological filters
W. Li, Véronique Haese-Coat, Joseph Ronsin · Proceedings - International Conference on Image Processing · 2002
In this paper, a quantitative evaluation methodology for morphological filters is presented. The goal of this evaluation scheme is to measure simultaneously the ability of morphological filters in edge sharpness preservation and noise suppression. A general morphological gradient criterion is proposed to divide an image into a series of regions according to its local spatial activity levels. The local mean-square-error (MSE) and local mean-absolute-error (MAE) are used to verify and compare performances of different tested filters. Several efficient and simple structured detail-preserving and noise-removal morphological filters are proposed and tested on simulated images by this scheme to prove its efficiency. For real image processing procedures, a combined filter structure is proposed to improve filter results.