AN ITERATIVE CLUSTERING PROCEDURE FOR INTERPRETING AN IMPERFECT LINE DRAWING

Abstract

Recovering three-dimensional shape of an object from a single line drawing is a classical problem in computer vision. Methods proposed range from Huffman–Clowes junction labeling, to Kanade's gradient space and skew symmetry analysis, to Sugihara's necessary and sufficient condition for a realizable polyhedral object, to Marill's MSDA shape recovery procedure, to Leclerc–Fischler's shape recovery procedure which assures planar faces, and to the recent Baird–Wang's gradient-descent algorithm which has a favorable time complexity. Yet all these assume perfect line drawings as the input. We propose a method that through the use of iterative clustering interprets an imperfect line drawing of a polyhedral scene. It distinguishes the true surface boundaries from the extraneous ones like the surface markings, fill-in the missing surface boundaries, and recovers 3-D shapes satisfying constraints of planarity of faces and parallel symmetry of lines, all at the same time. Experiments also show that the 3-D interpretation agrees with human perception.