Abstract
A novel integrated technique is proposed for hierarchical vectorization of electrical drawings in document images. Its first step includes recognition of different electrical symbols and their interconnections based on morphological operations and geometric analysis in three well-distinguished subspaces. This is followed by a hierarchical analysis for detecting the (series-or parallel-connected) super-components in an iterative manner. Finally a compact collection of circuit adjacency lists is produced, which are reduced further by binary encoding. Reconstruction algorithm has also been explained to merit the overall efficacy of the vectorization. Experimental results have been furnished to demonstrate its efficiency and robustness.
Similar content being viewed by others
References
M. Boraie and A. Balghonaim, “Optical recognition of electrical circuit drawings,” in Proc. IEEE Pacific Rim Conf. on Networking the Pacific Rim (1997), Vol. 2, pp. 843–846.
K. Broelemann, A. Dutta, X. Jiang, and J. Lladós, “Hierarchical graph representation for symbol spotting in graphical document images,” in Proc. SSPR/SPR (Hiroshima, 2012), pp. 529–538.
R. Cardoner and F. Thomas, “Efficient morphological set transformations on line drawings,” Int. J. Pattern Recogn. Artficial Intellig. 11 (6), 947–959 (1997).
J. Chen, M. K. Leung, and Y. Gao, “Noisy logo recognition using line segment Hausdorff distance,” Pattern Recogn. 36 (4), 943–955 (2003).
T. Cheng, J. Khan, H. Liu, and D. Yun, “A symbol recognition system,” in Proc. 2nd Int. Conf. on Document Analysis and Recognition, ICDAR’93 (Tsukuba, 1993), pp. 918–921.
A. Das and B. Chanda, “A fast algorithm for skew detection of document images using morphology,” Int. J. Doc. Anal. Recogn. 4, 109–114 (2001).
D. Dori, “Orthogonal zig-zag: An algorithm for vectorizing engineering drawings compared with Hough transform,” Adv. Eng. Software 28 (1), 11–24 (1997).
D. Dori and W. Liu, “Sparse pixel vectorization: an algorithm and its performance evaluation,” IEEE Trans. Pattern Anal. Mach. Intellig. 21 (3), 202–215 (1999).
D. Elliman, “A really useful vectorization algorithm,” in Proc. 3rd Int. Workshop on Graphics Recognition, Recent Advances, GREC’99 (2000), pp. 19–27.
Y. Fukada, “A primary algorithm for the understanding of logic circuit diagrams,” Pattern Recogn. 17 (1), 125–134 (1984).
R. P. Futrelle, M. Shao, C. Cieslik, and A. E. Grimes, “Extraction, layout analysis and classification of diagrams in pdf documents, in Proc. 7th Int. Conf. on Document Analysis and Recognition, ICDAR’03 (Edinburgh, 2003), pp. 1007–1014.
R. C. Gonzalez and R. E. Woods, Digital Image Processing, 2nd ed. (Addison-Wesley, Longman Publ., 1992).
F. C. A. Groen, A. C. Sanderson, and J. F. Schlag, “Symbol recognition in electrical diagrams using probabilistic graph matching,” Pattern Recogn. Lett. 3 (5), 343–350 (1985).
S. Kim, J. Suh, and J. Kim, “Recognition of logic diagrams by identifying loops and rectilinear polylines,” in Proc. 2nd Int. Conf. on Document Analysis and Recognition, ICDAR’93 (Tsukuba, 1993), pp. 349–352.
H. Kojima and T. Toida, “Online hand-drawn line-figure recognition and its application,” Pattern Recogn. 2, 1138–1142 (1988).
J. Li, A. Najmi, and R. Gray, “Image classification by a two-dimensional hidden Markov model,” IEEE Trans. Signal Proc. 48 (2), 517–533 (2000).
W. Liu, “On-line graphics recognition: state-of-art,” Proc. GREC 2003 Lecture Notes Comput. Sci. 4958, 291–304 (2004).
J. Lladós and G. Sánchez, “Graph matching versus graph parsing in graphics recognition: A combined approach,” Int. J. Pattern Recogn. Artificial Intellig. 18 (3), 455–473 (2004).
H. Luo, G. Agam, and I. Dinstein, “Directional mathematical morphology approach for line thinning and extraction of character strings from maps and line drawings,” in Proc. 3rd Int. Conf. on Document Analysis and Recognition, ICDAR’95 (1995), pp. 257–260.
M. M. Mano, Digital Logic and Computer Design (Prentice Hall PTR, 1979).
H. Murase and T. Wakahara, “Online hand-sketched figure recognition,” Pattern Recogn. 19 (2), 147–160 (1986).
A. Okazaki, S. Tsunekawa, T. Kondo, K. Mori, and E. Kawamoto, “An automatic circuit diagram reader with loop-structure-based symbol recognition,” IEEE Trans. Pattern Anal. Mach. Intell. 10 (3), 331–341 (1988).
N. Otsu, “A threshold selection method from gray-level histogram,” IEEE Trans. Syst. Man, Cybern. 9 (1), 62–66 (1979).
Y. J. Park and Y. B. Kwon, “An effective vector extraction method on architectural imaging using drawing characteristics,” in Proc. 4th Int. Workshop on Graphics Recognition Algorithms and Applications, GREC’01 (Springer-Verlag, London, 2002), pp. 299–309.
T. D. Pham, “Unconstrained logo detection in document images,” Pattern Recogn. 36 (12), 3023–3025 (2003).
D. Pucknell and K. Eshraghian, Basic VLSI Design, 3rd ed. (PHI, 2000).
M. Rashid, Spice for Circuits and Electronics Using PSPICE, 2nd ed. (Prentice Hall of India, 2000).
B. Sandhya, A. Agarwal, C. R. Rao, and R. Wankar, “Automatic gap identification towards efficient contour line reconstruction in topographic maps,” in Proc. 3rd Asia Int. Conf. on Modelling & Simulation, AMS’09 (Bandung, 2009), pp. 309–314.
J. Song, F. Su, C. L. Tai, and S. Cai, “An object-oriented progressive-simplification-based vectorization system for engineering drawings: Model, algorithm, and performance,” IEEE Trans. Pattern Anal. Mach. Intellig. 24 (8), 1048–1060 (2002).
S. Tabbone, “Indexing of technical line drawing based on f-signature,” in Proc. 6th Int. Conf. on Document Analysis and Recognition, ICDAR’01 (Seattle, 2001), pp. 1220–1224.
J. Valois, M. Côté, and M. Cheriet, “Online recognition of sketched electrical diagrams,” in Proc. 6th Int. Conf. on Document Analysis and Recognition, ICDAR’01 (Seattle, 2001), pp. 460–464.
Y. Wang, I. T. Phillips, and R. M. Haralick, “Document zone content classification and its performance evaluation,” Pattern Recogn. 39 (1), 57–73 (2006).
Y. Yu, A. Samal, and S. C. Seth, “A system for recognition a large class of engineering drawing,” IEEE Trans. Pattern Anal. Mach. Intellig. 19 (8), 868–890 (1997).
Author information
Authors and Affiliations
Corresponding author
Additional information
The article is published in the original.
Paramita De received her B.Sc. and M.Sc. degree in Computer Science from Vidyasagar University, Midnapur, India, in 2003 and 2005, respectively. She received her M. Tech. degree in Computer Science and Engineering from West Bengal University of Technology, Kolkata, India in 2008 and Ph.D. from Indian Institute of Engineering Science and Technology, Shibpur, Howrah, India in 2015. Presently, she is an Assistant Professor at Techno India University, Salt lake, Kolkata, India. Her current research area is digital image processing and pattern recognition. She has authored several research papers published in international journals and conferences.
Sekhar Mandal did his B.Tech. and M.Tech. from University of Calcutta, India, and his PhD from [Bengal Engineering and Science University, Shibpur, Howrah, India. He is currently an Associate Professor in Computer Science and Technology Department of Bengal Engineering and Science University, Shibpur, Howrah, India. His research interest mainly lies in digital image processing and pattern recognition. So far he has published 36 research papers in international journals, edited volumes, and refereed conference proceedings.
Partha Bhowmick graduated from the Indian Institute of Technology, Kharagpur, India, and received Ihis Masters and PhD degrees from the Indian Statistical Institute, Kolkata, India. Currently he is Associate Professor in Computer Science and Engineering Department, Indian Institute of Technology, Kharagpur, India. His research focus primarily is digital geometry, with applications to combinatorial image analysis and computer graphics. He has coauthored over 100 research papers in these areas, which have been published in peer-reviewed international journals, edited volumes, and international conference proceedings. He has also coauthored one book in digital geometry, and he holds 4 US patents.
Rights and permissions
About this article
Cite this article
De, P., Mandal, S. & Bhowmick, P. Hierarchical vectorization of electrical drawings in document images by connectivity analysis of symbols and super-components. Pattern Recognit. Image Anal. 27, 309–325 (2017). https://doi.org/10.1134/S1054661817020079
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S1054661817020079