Scribble vectorization using concentric sampling circles

Abstract

In this paper we introduce a path extraction algorithm for multi-stroke scribbled paths by making use of path-centred concentric sampling circles. Circle and line geometry is then exploited to efficiently obtain piece-wise linear models of the multi-stroke segments in the drawing. Parzen-window estimation is used to obtain the probability distribution of the grey-level profile of the sampling circles to determine the intersecting angle of the sampling circle with the stroke segments and hence determine the line model parameters. The results obtained show that the algorithm identifies the line models accurately while reducing considerably the computational time required to obtain the line models.