Segmentation of brush strokes by saliency preserving dual graph contraction

Abstract

Brush strokes are segmented from works of art by a combination of filtering and grouping. Filtering yields local evidence for crossings and lines. Grouping is done on two levels of scale and abstraction. The first level is a dual pair (G u, G u) of attributed plane graphs, the vertex and edge attributes of which are derived from the filtering. The result of the grouping on this level is given by a topological minor G top of G u . The derivation of G top from G u is done by dual graph contraction, i.e. by parallel steps, each of which involves only local operations on G u and G u . This step is shown to preserve connections via most salient paths. On the second level consecutive edges of G top are grouped to strokes which are consistent with our model of strokes from superimposed brush moves. Experimental results are presented for portrait miniatures.