Abstract
This paper presents a hybrid method to use both the idea of projection and Toeplitz Matrix approaches to describe the feature vectors of an image and hence identifying it. The method applies two different tools. The main one is Toeplitz forms and the second is Neural Networks. The image model considered in this work are some selected Arabic scripts. The letter is first projected on 12 axes, then the lengths of these axes are measured and afterwards for the sake of classification and recognition these lengths are compared with the ones in the data base. The method has proved its high efficiency upon the other known approaches. Toeplitz model has shown its successful role in improving the description of the image feature vectors and hence increasing the rate of recognition. The overall algorithm has reached a very low rate of misclassification. Both machine and hand written cases have been studied. In this paper, examples of handwritten scripts are considered.
This is a preview of subscription content, log in via an institution to check access.
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
Saeed, K.: A Projection Approach for Arabic Handwritten Characters Recognition. In: Sincak, P., Vascak, J. (eds.) Quo Vadis Computational Intelligence? New Trends and App. in Comp. Intelligence, pp. 106–111. Physica-Verlag, Berlin (2000)
Burr, D.: “Experiments on Neural Net Recognition of Spoken and Written Text. IEEE Trans. On Acoustic, Speech and Signal Proc. 36(7), 1162–1168 (1988)
Zurada, J., Barski, M., Jedruch, W.: Artificial Neural Networks. PWN, Warszawa (1996) (in Polish)
Saeed, K., Rybnik, M., Tabedzki, M.: Implementation and Advanced Results on the Non-interrupted Skeletonization Algorithm. In: 9th CAIP Int. Conference on Computer Analysis of Images and Patterns, September 5-7, Warsaw (2001); Proceedings published in: Lecture Notes in Computer Science - Skarbek, W. (Ed.), Computer Analysis of Images and Patterns, pp. 601–609, Springer-Verlag Heidelberg, Berlin (2001)
Saeed, K.: Computer Graphics Analysis: A Method for Arbitrary Image Shape Description. MGV - International Journal on Machine Graphics and Vision, Institute of Computer Science 10(2), 185–194 (2001)
Saeed, K., Tabedzki, M., Adamski, M.: A New Approach for Object-Feature Extract and Recognition. In: 9th International Conference on Advanced Computer Systems - ACS 2002, Miedzyzdroje, October 23-25, pp. 389–397 (2002)
Saeed, K.: New Approaches for Cursive Languages Recognition: Machine and Hand Written Scripts and Texts. In: Advances in Neural Networks and Applications, pp. 92–97. WSES Press, Tenerife (2001)
Riedmiller, M., Braun, H.: RPROP - A Fast Adaptive Learning Algorithm, Technical Report, Karlsruhe University (1992)
Goraine, H.: Application of Neural Networks on Cursive Text Recognition. In: Advances in Signal Processing and Computer Technologies, pp. 350–354. WSES/IEEE, WSES Press (2001)
Tadeusiewicz, R.: Neural Networks. AOW, Cracow (1992) (in Polish)
Saeed, K., Kozlowski, M.: An Image-Based System for Spoken-Letter Recognition. In: Pietkov, M. (ed.) Computer Analysis of Images and Patterns. LNCS, pp. 494–502. Springer, Heidelberg (2003)
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
Saeed, K., Tabedzki, M. (2004). Cursive-Character Script Recognition Using Toeplitz Model and Neural Networks. In: Rutkowski, L., Siekmann, J.H., Tadeusiewicz, R., Zadeh, L.A. (eds) Artificial Intelligence and Soft Computing - ICAISC 2004. ICAISC 2004. Lecture Notes in Computer Science(), vol 3070. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-24844-6_100
Download citation
DOI: https://doi.org/10.1007/978-3-540-24844-6_100
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-22123-4
Online ISBN: 978-3-540-24844-6
eBook Packages: Springer Book Archive