This Article 
 Bibliographic References 
 Add to: 
Vector-Based Arc Segmentation in the Machine Drawing Understanding System Environment
November 1995 (vol. 17 no. 11)
pp. 1057-1068

Abstract—Arcs are important primitives in engineering drawings. Along with bars, they play a major role in describing both the geometry and the annotation of the object represented in the drawing. Extracting these primitives during the lexical analysis phase is a prerequisite to syntactic and semantic understanding of engineering drawings within the Machine Drawing Understanding System. Bars are detected by the orthogonal zig-zag vectorization algorithm. Some of the detected bars are linear approximations of arcs. As such, they provide the basis for arc segmentation. An arc is detected by finding a chain of bars and a triplet of points along the chain. The arc center is first approximated as the center of mass of the triangle formed by the intersection of the perpendicular bisectors of the chords these points define. The location of the center is refined by recursively finding more such triplets and converging to within no more than a few pixels from the actual arc center after two or three iterations. The high performance of the algorithm, demonstrated on a set of real engineering drawings, is due to the fact that it avoids both raster-to-vector and massive pixel-level operations, as well as any space transformations.

[1] R. Kasturi, S.T. Bow, W. El-Masri, J. Shah, J.R. Gattikermes, and U.B. Mokate, "A System for Interpretation of Line Drawings," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 12, no. 10, pp. 978-992, Oct. 1990.
[2] D. Dori,Y. Liang,J. Dowel,, and I. Chai,“Sparse pixel recognition of primitives in engineering drawings,” Machine Vision and Applications, vol. 6, pp. 69-82, 1993.
[3] D. Dori,“A syntactic/geometric approach to recognition of dimensions in engineering machine drawings,” Computer Vision, Graphics, and Image Processing, vol. 47, pp. 1-21, 1989.
[4] I. Chai and D. Dori,“Orthogonal zig-zag: An efficient method for extracting bars in engineering drawings,” Visual Form, C. Arcelli, L.P. Cordella, and G. Sanniti di Baja, eds. New York and London: Plenum Press, pp. 127-136, 1992.
[5] D. Dori,“Object-process analysis: Maintaining the balance between system structure and behavior,” J. Logic and Computation, vol. 5, no. 2, pp. 227-249, 1995.
[6] D. Dori,“Representing pattern recognition-embedded systems through object-process diagrams: The case of the Machine Drawing UnderstandingSystem,” Pattern Recognition Letters, vol. 16, no. 4, pp. 377-384, 1995.
[7] B. Smith and J. Wellington,“Initial graphics exchange specification,” Nat’l Inst. of Standards, Gaithersburg, Md., 1986.
[8] I. Chai and D. Dori,“Extraction of text boxes from engineering drawings,” Proc. Soc. Photo-Optical Instrumentation Engineers—Int’l Soc. Optical Eng.(SPIE)/Soc. Imaging Science and Technology (IS&T) Symp. Electronic ImagingScience and Technology, Conf. Character Recognition and Digitizer Technologies, SPIE vol. 1,661, pp. 38-49,San Jose, Calif., Feb.10-12, 1992.
[9] D. Dori and A. Pnueli,“The grammar of dimensions in machine drawings,” Computer Vision, Graphics, and Image Processing, vol. 42, pp. 1-18, 1988.
[10] D. Dori,“Dimensioning analysis: A step towards automatic high level understanding of engineering drawings,” Comm. ACM, vol. 35, no. 10, pp. 92-103, Oct. 1992.
[11] D.H. Ballard,“Generalizing the Hough transform to detect arbitrary shapes,” Pattern Recognition, vol. 13, no. 2, pp. 111-122, 1981.
[12] D.J. Hunt and L.W. Nolte,“Performance of the Hough transform and its relationship to statistical signal detection theory,” Computer Vision, Graphics, and Image Processing, vol. 43, pp. 221-238, 1988.
[13] J. Illingworth, E.J. Kittler, “The Adaptive Hough Transform,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 9, no. 5, pp. 690-697, May 1987.
[14] R.M. Haralick and L.G. Shapiro, Computer and Robot Vision. New York: Addison-Wesley, 1993.
[15] R.S. Conker,“A dual plane variation of the Hough transform for detecting nonconcentric circles of different radii,” Computer Vision, Graphics, and Image Processing, vol. 43, pp. 115-132, 1988.
[16] C. Kimme,D.H. Ballard,, and J. Sklansky,“Finding circles by an array of accumulators,” CACM, vol. 18, pp. 120-122, 1975.
[17] L. O’Gorman and A.C. Sanderson,“The converging squares algorithm: An efficient method for locating peaks in multidimensions,” IEEE Trans. Pattern Analysis and Machine Intelligence, pp. 280-288, 1984.
[18] H. Asada and M. Brady, “The Curvature Primal Sketch,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 8, pp. 2-14, 1986.
[19] P.L. Rosin and G.A.W. West, “Segmentation of Edges into Lines and Arcs,” Image Vision Computing, vol. 7, pp. 109-114, 1989.
[20] L. O’Gorman,“Curvilinear feature detection from curvature estimation,” Proc. Ninth ICPR, pp. 116-119,Rome, Nov. 1988.
[21] L. O’Gorman,“An analysis of feature detectability from curvature estimation,” Proc. CVPR, Ann Arbor, Mich., June 1988.
[22] D.G. Lowe, “Three-Dimensional Object Recognition from Single Two-Dimensional Images,” Artificial Intelligence, vol. 31, pp. 355-395, 1987.

Index Terms:
Arc segmentation, engineering drawing understanding, technical documentation automation, sparse-pixel recognition, document analysis and recognition, vectorization, raster-to-vector, Hough transform.
Dov Dori, "Vector-Based Arc Segmentation in the Machine Drawing Understanding System Environment," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 17, no. 11, pp. 1057-1068, Nov. 1995, doi:10.1109/34.473231
Usage of this product signifies your acceptance of the Terms of Use.