Abstract
We propose an approach dedicated to recognize characters from binary images by an hybrid strategy. A statistical method is used to identify the global shape of each alphanumeric symbol. The recognition is managed by a Hierarchical Neural Network (HNN), that is able to deal with topological errors in the contour extraction. This strategy is extremely efficient for the majority of the classes: the recognition rate reaches about 99.5%. However, the performances sensitively decrease for ’similar characters’, i.e. ’8’/’B’. In that case, we adopt a strategy that revolves around decomposing the characters into structural elements. The Reeb graph generated from the binary images and a simple polygonal approximation permit to capture both topological and geometrical relevant features. The classification stage is carried out by a boosting algorithm.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Zhang, D., Lu, G.: Review of shape representation and description techniques. Pattern Recognition 37(1) (2004)
Bremananth, R., Chitra, A.: A robust video based license plate recognition system. ICISIP (2005)
Shridhar, M., Badreldi, A.: High accuracy character recognition algorithm using fourier and topological descriptors. Patt. Recogn. 17(5), 515–524 (1984)
Kopf, S., Haenselmann, T., Effelsberg, W.: Enhancing Curvature Scale Space Features for Robust Shape Classification. In: Proceedings of IEEE International Conference on Multimedia and Expo (ICME 2005), Amsterdam, The Netherlands (2005)
Broumandnia, A., Shanbehzadeh, J.: Fast zernike wavelet moments for farsi character recognition. Image Vision Comput. 25(5), 717–726 (2007)
Cash, G., Hatamian, A.: Optical character recognition by the method of moments. 39(3), 291–310 (1987)
Pavlidis, T.: 36 years on the pattern recognition front. Pattern Recognition Letters 24, 1–7 (2003)
Cordella, L.P., Vento, M.: Symbol recognition in documents: a collection of techniques? IJDAR 3(2), 73–88 (2000)
Hilaire, X., Tombre, K.: Robust and accurate vectorization of line drawings. IEEE Transactions on Pattern Analysis and Machine Intelligence 28(6), 890–904 (2006)
Burge, M., Kropatsch, W.: A minimal line property preserving representation of line images. Computing 62(4), 355–368 (1999)
Lam, L., Lee, S.W., Suen, C.Y.: Thinning methodologies - a comprehensive survey, 61–77 (1995)
Kälviäinen, H., Hirvonen, P., Xu, L., Oja, E.: Probabilistic and non-probabilistic hough transforms: overview and comparisons. Image Vision Comput. 13(4), 239–252 (1995)
Pan, X., Ye, X., Zhang, S.: A hybrid method for robust car plate character recognition. Engineering Applications of Artificial Intelligence, 963–972 (2005)
Reeb, G.: Sur les points singuliers d’une forme de pfaff complément intégrable ou d’une fonction numérique. Comptes Rendus de L’Académie ses Séances, 847–849 (1946)
Peerson, E., Fu, K.: Shape discrimination using fourier descriptor. Trans. Syst. Man, Cybern. SMC-7(3), 170–179 (1977)
Kauppinen, H., Seppanen, T., Pietikainen, M.: An experimental comparison of autoregressive and fourier-based descriptors in 2d shape classification. IEEE Transactions on Pattern Analysis and Machine Intelligence 17(2), 201–207 (1995)
Zhang, D., Lu, G.: Content-based shape retrieval using different shape descriptors: A comparative study. icme 00, 289 (2001)
Arbter, K., Snyder, W.E., Burhardt, H., Hirzinger, G.: Application of affine-invariant fourier descriptors to recognition of 3-d objects. IEEE Trans. Pattern Anal. Mach. Intell. 12(7), 640–647 (1990)
Folkers, A., Samet, H.: Content-based image retrieval using fourier descriptors on a logo database. In: ICPR 2002: Proceedings of the 16 th International Conference on Pattern Recognition (ICPR 2002), vol. 3, IEEE Computer Society, Washington, DC, USA (2002)
Devi, S., Panda, S., Shyam, S., Pattnik, D., Khuntia, B.: Initializing artificial neural networks by genetic algorithm to calculate the resonant frequency of single shorting post rectangular patch antenna. In: IEEE Antennas and Propagation Society International Symposium, pp. 144–147 (2003)
Vacavant, A., Coeurjolly, D., Tougne, L.: Topological and geometrical reconstruction of complex objects on irregular isothetic grids. In: Kuba, A., Nyúl, L.G., Palágyi, K. (eds.) DGCI 2006. LNCS, vol. 4245, pp. 470–481. Springer, Heidelberg (2006)
Coeurjolly, D.: Supercover model and digital straight line recognition on irregular isothetic grids. In: Andrès, É., Damiand, G., Lienhardt, P. (eds.) DGCI 2005. LNCS, vol. 3429, pp. 311–322. Springer, Heidelberg (2005)
Schapire, R.: The boosting approach to machine learning: An overview (2001)
Selman, B., Levesque, H.J., Mitchell, D.G.: A new method for solving hard satisfiability problems. In: AAAI, pp. 440–446 (1992)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Thome, N., Vacavant, A. (2007). A Combined Statistical-Structural Strategy for Alphanumeric Recognition. In: Bebis, G., et al. Advances in Visual Computing. ISVC 2007. Lecture Notes in Computer Science, vol 4842. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-76856-2_52
Download citation
DOI: https://doi.org/10.1007/978-3-540-76856-2_52
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-76855-5
Online ISBN: 978-3-540-76856-2
eBook Packages: Computer ScienceComputer Science (R0)