Title :
Arc segmentation by stepwise recovery of vectorized pieces
Author :
Dori, Dov ; Wenyin, Liu
Author_Institution :
Fac. of Ind. Eng. & Manage., Technion-Israel Inst. of Technol., Haifa, Israel
Abstract :
Accurate arc segmentation is essential for high-level engineering drawing understanding and 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 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 vectorization process and meet the continuity conditions of the same circular arc. Proper threshold selection and consistent checking of co-circularity of the assumed arc pieces result in accurate circular arcs. Experimental results are presented and discussed
Keywords :
geometry; image recognition; image reconstruction; image segmentation; object recognition; arc segmentation; circular arcs; co-circularity; continuity condition; geometry objects; high-level engineering drawing; multicomponent objects; recognition; sequential stepwise recovery; stepwise recovery; threshold selection; vectorization process; vectorized pieces; wire fragments; Clustering algorithms; Engineering drawings; Engineering management; Feature extraction; Geometry; Image segmentation; Industrial engineering; Object detection; Shape; Technology management;
Conference_Titel :
Electrical and Electronics Engineers in Israel, 1996., Nineteenth Convention of
Conference_Location :
Jerusalem
Print_ISBN :
0-7803-3330-6
DOI :
10.1109/EEIS.1996.566930
