Dimension sets detection in technical drawings

This paper is primarily devoted to an algorithm for detecting dimension sets in engineering drawings that are drawn to ISO drafting standards. Our approach joins those starting with detection of dimension text while most methods are started with the detection of arrowheads. First, we detect among the segments and arcs resulting from the vectorization process those that fulfill some location constraints. A number of segments and arcs are chosen to be candidate parts of dimension lines according to the position and the geometry of their presumed witness lines. We establish the link between the candidates and the detected primitives which are in correspondence with text blocks. Complete dimension lines are found using tracking and fusion processes. Arrowheads are then located thanks to the position of witness and dimension lines. Experimental results are presented.

[1]  George Markowsky,et al.  Fleshing out projections , 1981 .

[2]  Robert M. Haralick,et al.  Understanding engineering drawings , 1982, Comput. Graph. Image Process..

[3]  Dov Dori,et al.  The grammar of dimensions in machine drawings , 1988, Comput. Vis. Graph. Image Process..

[4]  Rangachar Kasturi,et al.  A Robust Algorithm for Text String Separation from Mixed Text/Graphics Images , 1988, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Geoff A. W. West,et al.  Segmentation of edges into lines and arcs , 1989, Image Vis. Comput..

[6]  Dov Dori,et al.  A syntactic/geometric approach to recognition of dimensions in engineering machine drawings , 1989, Comput. Vis. Graph. Image Process..

[7]  Jr. Daniel Bohdan Lysak.  Interpretation of engineering drawings of polyhedral and non-polyhedral objects from orthographic projections , 1991 .

[8]  Suzanne Collin,et al.  Analysis of Technical Documents: The REDRAW System , 1992 .

[9]  Suzanne Collin.  Interprétation de la cotation des dessins techniques par analyse syntaxique , 1992 .

[10]  Zesheng Tang,et al.  Recognition of dimensions in engineering drawings based on arrowhead , 1993, Proceedings of 2nd International Conference on Document Analysis and Recognition (ICDAR '93).

[11]  Zesheng Tang,et al.  Using web grammar to recognize dimensions in engineering drawings , 1993, Pattern Recognit..

[12]  Rangachar Kasturi,et al.  Detection of Dimension Sets in Engineering Drawings , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[13]  Gabriella Sanniti di Baja.  Well-Shaped, Stable, and Reversible Skeletons from the (3, 4)-Distance Transform , 1994, J. Vis. Commun. Image Represent..

[14]  Suzanne Collin,et al.  Syntactic Analysis of Technical Drawing Dimensions , 1994, Int. J. Pattern Recognit. Artif. Intell..

[15]  Chuan-Kang Ting,et al.  A new approach for detection of dimensions set in mechanical drawings , 1997, Pattern Recognit. Lett..

[16]  Christian Ah-Soon,et al.  Stable, robust and off-the-shelf methods for graphics recognition , 1998, Proceedings. Fourteenth International Conference on Pattern Recognition (Cat. No.98EX170).