Abstract
Recognition of old Greek manuscripts is essential for quick and efficient content exploitation of the valuable old Greek historical collections. In this paper, we focus on the problem of recognizing early Christian Greek manuscripts written in lower case letters. Based on the existence of hole regions in the majority of characters and character ligatures in these scripts, we propose a novel, segmentation-free, fast and efficient technique that assists the recognition procedure by tracing and recognizing the most frequently appearing characters or character ligatures. First, we detect hole regions that exist in the character body. Then, the protrusions in the outer contour outline of the connected components that contain the character hole regions are used for the classification of the area around holes to a specific character or a character ligature. The proposed method gives highly accurate results and offers great assistance to old Greek handwritten manuscript OCR.
Chapter PDF
Similar content being viewed by others
References
Verma, B., Blumenstein, M., Kukarni, S.: Recent Achievements in Off-line Handwriting Recognition Systems. In: International Conference on Computational Intelligence and Multimedia Applications (ICCIMA 1998), Melbourne, Australia, pp. 27–33 (1998)
Lam, L., et al.: Automatic Processing of Information on Cheques. In: International Conference on Systems, Man & Cybernetics, pp. 2353–2358 (1995)
Brakensiek, A., Rottland, J., Rigoll, G.: Confidence measures for an address reading system. In: Seventh International Conference on Document Analysis and Recognition (ICDAR 2003), pp. 294–298 (2003)
Suen, C.Y., et al.: Building a New Generation of Handwriting Recognition Systems. Pattern Recognition Letters 14, 303–315 (1993)
Guillevic, D., Suen, C.Y.: HMM Word Recognition Engine. In: Fourth International Conference on Document Analysis and Recognition (ICDAR 1997), p. 544 (1997)
Kavallieratou, E., Fakotakis, N., Kokkinakis, G.: Handwritten character recognition based on structural characteristics. In: 16th International Conference on Pattern Recognition, pp. 139–142 (2002)
Eastwood, B., et al.: A Feature Based Neural Network Segmenter for Handwritten Words. In: International Conference on Computational Intelligence and Multimedia Applications (ICCIMA 1997), Australia, pp. 286–290 (1997)
Chen, C.H., de Curtins, J.: Word Recognition in a Segmentation-Free Approach to OCR. In: Second International Conference on Document Analysis and Recognition (ICDAR 1993), pp. 573–576 (2003)
Chen, C.H., de Curtins, J.: A Segmentation-free Approach to OCR. In: IEEE Workshop on Applications of Computer Vision, pp. 190–196 (1992)
Pavlidis, T.: Algorithms for Graphics and Image Processing. Computer Science Press, Rockville (1992)
Xia, F.: Normal vector and winding number in 2D digital images with their application for hole detection. Pattern Recognition 36, 1383–1395 (2003)
Jain, A.: Fundamentals of digital image processing. Prentice-Hall, Englewood Cliffs (1989)
Theodoridis, S., Koutroumbas, K.: Pattern Recognition. Academic Press, London (1997)
Chang, C.-C., Lin, C.-J.: LIBSVM: A library for support vector machines (2001), Software available at http://www.csie.ntu.edu.tw/cjlin/libsvm
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Gatos, B., Ntzios, K., Pratikakis, I., Petridis, S., Konidaris, T., Perantonis, S.J. (2004). A Segmentation-Free Recognition Technique to Assist Old Greek Handwritten Manuscript OCR. In: Marinai, S., Dengel, A.R. (eds) Document Analysis Systems VI. DAS 2004. Lecture Notes in Computer Science, vol 3163. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-28640-0_7
Download citation
DOI: https://doi.org/10.1007/978-3-540-28640-0_7
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-23060-1
Online ISBN: 978-3-540-28640-0
eBook Packages: Springer Book Archive
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
