Stepwise recovery of arc segmentation in complex line environments

Abstract.

Accurate arc segmentation, essential for high-level engineering drawing understanding, is very difficult due to noise, clutter, tangency, and intersections with other geometry objects. We present an application of a generic methodology for recognition of multicomponent graphic objects in engineering drawings to the segmentation of circular arcs. The underlying mechanism is a sequential stepwise recovery of components that are segmented as wire fragments during the sparse-pixel vectorization process and meet a set of continuity conditions. Proper threshold selection and consistent checking of co-circularity of the assumed arc pieces result in an accurate arc segmentation method. Experimental results are presented, evaluated by an objective protocol, and discussed.