Abstract
In this article we try to make different kinds of information cooperate in a characters recognition system addressing old Greek and Egyptians documents. We first use a statistical approach based on classical shape descriptors (Zernike, Fourier). Then we use a structural classification method with an attributed graph description of characters and a random graph modeling of classes. The hypothesis, that structural methods bring topological information that statistical methods do not, is validated on Greek characters. A cooperation with a chain of classifiers based on reject management is then proposed. Due to computation cost, the goal of such a chain is to use the structural approach only if the statistical one fails.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Bellili, A., Gilloux, M., Gallinari, P.: An mlp-svm combination architecture for offline handwritten digit recognition: Reduction of recognition errors by support vector machines rejection mechanisms. IJDAR 5, 244–252 (2003)
Trier, O.D., Jain, A.K., Taxt, T.: Feature-extraction methods for character-recognition: A survey. PR 29, 641–662 (1996)
Kang, K.W., Kim, J.H.: Handwritten hangul character recognition with hierarchical stochastic character representation. In: ICDAR (2003)
Chan, K., Cheung, Y.: Fuzzy-attribute graph with application to chinese character recognition. SMC 22, 402–410 (1992)
Cho, S.Y., Kim, J.H.: Bayesian network modeling of hangul characters for on-line handwriting recognition. In: ICDAR (2003)
Foggia, P., Sansone, C., Tortorella, F., Vento, M.: Combining statistical and structural approaches for handwritten character description. IVC 17, 701–711 (1999)
Rahman, A., Fairhurst, M.: Multiple classifier decision combination strategies for character recognition: A review. IJDAR 5, 166–194 (2003)
Kuncheva, L.I., Bezdek, J.C., Duin, R.P.: Decision templates for multiple classifier fusion: An experimental comparison. PR 34, 299–314 (2001)
Alpaydin, E., Kaynak, C., Alimoglu, F.: Cascading multiple classifiers and representations for optical and pen-based handwritten digit recognition. In: IWFHR (2000)
Zhang, D., Lu, G.: A comparative study of curvature scale space and fourier descriptors for shape-based image retrieval. JVCIR 14, 39–57 (2002)
Khotanzad, A., Hong, Y.: Invariant image recognition by zernike moments. PAMI 12, 489–497 (1990)
Chong, C., Raveendran, P., Mukundan, R.: A comparative analysis of algorithms for fast computation of zernike moments. PR 36, 731–742 (2003)
Damiand, G., Bertrand, Y., Fiorio, C.: Topological model for 2d image representation: Definition and optimal extraction algorithm. Computer Vision and Image Understanding 93, 111–154 (2004)
Blum, H.: A transformation for extracting new descriptions of shape. In: Models for the Perception of Speech and Visual Form, pp. 362–380. MIT Press, Cambridge (1967)
Lam, L., Lee, S.W., Suen, C.Y.: Thinning methodologies - a comprehensive survey. IEEE Transactions on Pattern Analysis and Machine Intelligence 14, 869–885 (1992)
Zhang, Y.Y., Wang, P.S.P.: A new parallel thinning methodology. PRAI 8, 999–1011 (1994)
Lu, S., Ren, Y., Suen, C.: Hierarchical attributed graph representation and recognition of handwritten chinese characters. PR 24, 617–632 (1991)
Serratosa, F., Sanfeliu, A.: Function-described graphs for structural pattern recognition. Technical report, Universitat Rovira i Virgili, Tarragona, Spain (1999)
Kim, H., Kim, J.: Hierarchical random graph representation of handwritten characters and its application to hangul recognition. PR 34, 187–201 (2001)
Ranganath, H., Chipman, L.: A fuzzy relaxation algorithm for matching imperfectly segmented images to models. In: IEEE Southeastcon 1992, vol. 1, pp. 128–136 (1992)
Dubuisson, B.: Diagnostic et reconnaissance des formes. In: Diagnostic, Intelligence Artificielle et Reconnaissance des Formes. Traité ic2 diagnostic edn. Hermés Science, pp. 107–140. Hermés Science (2001)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Arrivault, D., Richard, N., Fernandez-Maloigne, C., Bouyer, P. (2005). Collaboration Between Statistical and Structural Approaches for Old Handwritten Characters Recognition. In: Brun, L., Vento, M. (eds) Graph-Based Representations in Pattern Recognition. GbRPR 2005. Lecture Notes in Computer Science, vol 3434. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-31988-7_28
Download citation
DOI: https://doi.org/10.1007/978-3-540-31988-7_28
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-25270-2
Online ISBN: 978-3-540-31988-7
eBook Packages: Computer ScienceComputer Science (R0)