Abstract
Symbol recognition is important in many applications such as the automated interpretation of line drawings and retrieval-by-content search engines. This paper presents the use of geometric matching for symbol recognition under similarity transformations. We incorporate this matching approach in a complete symbol recognition/spotting system, which consists of denoising, symbol representation and recognition. The proposed system works for both isolated recognition and spotting symbols in context. For denoising, we use an adaptive preprocessing algorithm. For symbol representation, pixels and/or vectorial primitives can be used, then the recognition is done via geometric matching. When applied on the datasets of GREC’05 and GREC’11 symbol recognition contests, the system has performed significantly better than other statistical or structural methods.
Access provided by Autonomous University of Puebla. Download to read the full chapter text
Chapter PDF
Similar content being viewed by others
References
Breuel, T.M.: Implementation techniques for geometric branch-and-bound matching methods. CVIU 90(3), 258–294 (2003)
Coustaty, M., Guillas, S., Visani, M., Bertet, K., Ogier, J.-M.: On the Joint Use of a Structural Signature and a Galois Lattice Classifier for Symbol Recognition. In: Liu, W., Lladós, J., Ogier, J.-M. (eds.) GREC 2007. LNCS, vol. 5046, pp. 61–70. Springer, Heidelberg (2008)
Locteau, H., Adam, S., Trupin, É., Labiche, J., Héroux, P.: Symbol Recognition Combining Vectorial and Statistical Features. In: Liu, W., Lladós, J. (eds.) GREC 2005. LNCS, vol. 3926, pp. 76–87. Springer, Heidelberg (2006)
Locteau, H., Adam, S., Trupin, E., Labiche, J., Heroux, P.: Symbol spotting using full visibility graph representation. In: GREC, pp. 1–7 (2007)
Luqman, M.M., Brouard, T., Ramel, J.: Graphic symbol recognition using graph based signature and bayesian network classifier. In: ICDAR, pp. 1325–1329 (2009)
Min, F., Zhang, W., Wenyin, L.: Symbol Recognition Using Bipartite Transformation Distance and Angular Distribution Alignment. In: Liu, W., Lladós, J. (eds.) GREC 2005. LNCS, vol. 3926, pp. 398–407. Springer, Heidelberg (2006)
Nayef, N., Breuel, T.M.: Graphical symbol retrieval using a branch and bound algorithm. In: ICIP, pp. 2153–2156 (2010)
Nguyen, T., Tabbone, S., Boucher, A.: A symbol spotting approach based on the vector model and a visual vocabulary. In: ICDAR, pp. 708–712 (2009)
Qureshi, R.J., Ramel, J.-Y., Barret, D., Cardot, H.: Spotting Symbols in Line Drawing Images Using Graph Representations. In: Liu, W., Lladós, J., Ogier, J.-M. (eds.) GREC 2007. LNCS, vol. 5046, pp. 91–103. Springer, Heidelberg (2008)
Rusiñol, M., Lladós, J., Sánchez, G.: Symbol spotting in vectorized technical drawings through a lookup table of region strings. Pattern Analysis and Applications 13(3), 321–331 (2010)
Su, F., Lu, T., Yang, R.: Symbol recognition combining vectorial and pixel-level features for line drawings. In: 20th International Conference on Pattern Recognition (ICPR), pp. 1892–1895 (2010)
Wong, A., Bishop, W.: Robust invariant descriptor for symbol-based image recognition and retrieval. In: IEEE Int. Conf. on Semantic Computing, pp. 637–644 (2007)
Yang, S.: Symbol recognition via statistical integration of pixel-level constraint histograms: A new descriptor. PAMI 27(2), 278–281 (2005)
Zhang, J., Zhang, W., Wenyin, L.: Adaptive Noise Reduction for Engineering Drawings Based on Primitives and Noise Assessment. In: Liu, W., Lladós, J. (eds.) GREC 2005. LNCS, vol. 3926, pp. 140–150. Springer, Heidelberg (2006)
Zhang, W., Wenyin, L.: A new vectorial signature for quick symbol indexing, filtering and recognition. In: ICDAR, pp. 536–540 (2007)
Zhang, W., Wenyin, L., Zhang, K.: Symbol recognition with kernel density matching. PAMI 28(12), 2020–2024 (2006)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Nayef, N., Breuel, T.M. (2013). On the Use of Geometric Matching for Both: Isolated Symbol Recognition and Symbol Spotting. In: Kwon, YB., Ogier, JM. (eds) Graphics Recognition. New Trends and Challenges. GREC 2011. Lecture Notes in Computer Science, vol 7423. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-36824-0_4
Download citation
DOI: https://doi.org/10.1007/978-3-642-36824-0_4
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-36823-3
Online ISBN: 978-3-642-36824-0
eBook Packages: Computer ScienceComputer Science (R0)