Residues of morphological filtering by reconstruction for texture classification

摘要

This paper presents a set of texture features which is based on morphological residues of opening and closing by reconstruction. In texture classification, this set of features is proven much more robust to noise than the feature set derived from traditional morphological residues. An optimization algorithm is established to search for the optimum feature subset. The robustness to noise of our feature set is investigated in detail qualitatively and quantitatively. In various noise circumstances as well as in image deformation, it is found that this feature set bears quite high texture classification accuracy compared to other texture classification methods.