Morphological Algorithm for Color Objects Classification

摘要

A mathematical morphology based approach for automated classification of color objects is explored in this paper. Using an adapted set of mathematical morphology operators, the initial color images are analyzed until final color classification is accomplished. Morphological feature extraction algorithm includes morphological color gradient, homotopic skeleton, Hit-or-Miss transform and other special morphological processing steps. In the end, illustrative application examples of the presented approach on real acquired images are also provided.