Abstract
This article presents a new model (based on Muqla idea) used in recognition of cursive letters. It is used for creating feature vectors based on Toeplitz matrices. As the approach is used for the first time, no comparison had been made from modelling point of view. However, the way of feature vectors extraction in this approach showed its simplicity and may find its practical applications in processing and verifying both written and spoken texts. The suggested algorithm makes it possible to reduce the limiting factors [1] in recognition as it is easy to extend it to cover more vocabulary, syntax or semantic information.
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
R. A. Cole, Editor in Chief, âSurvey of the State of the Art in Human Language Technology,â Cambridge University Press, 1996.
M. H. Hassan, R. Kurowski, âAn Introductory Course to Arabic Language,â WP, Cracow 1972.
K. Saeed, R. Niedzielski, âA Fast Recognition Structured Algorithm of Typewritten Cursive Scripts,âProceedings of 6th Conference of PTSK on Simulation in Research and Development(in Polish), pp. 67â71, BialystokBialowieza 1999.
K. Saeed, âA Projection Approach for Arabic Handwritten Characters Recognition,âProc. of International Symposium on Computational Intelligence- ISCI Aug. 31stâ Sep. 1stKosice 2000, Slovakia. (Accepted for publication and presentation).
K. Saeed, âOn the realization of digital filters,âProceedings of 1st International Conference on Digital Signal Processing and its ApplicationsDSPAâ98,Vol. 1, pp. 141â143,Moscow, 1998.
K. Saeed, R. Niedzielski, âExperiments on Thinning of Cursive-Style Alphabets,â Inter. Conf. on Information Technologies ITESBâ99June 24â25, Minsk 1999.
M. J. Nalewajko, âUniversal system for recognition of scripts using artificial neural networks,â M.Sc. Thesis, Faculty of Computer Science Technical University of Bialystok,Bialystok, July 1999.
K. Saeed,âThree-Agent System for Cursive-Scripts Recognition,â Proc. CVPRIP â2000 Computer Vision,Pattern Recognition and Image Proc.The 5th Joint Conf. on Information Sciences JCIS2000,Feb. 27th â March 3rd 2000, New Jersey, USA.
Burr, "Experiments on Neural Net Recognition of Spoken and Written Text," IEEE Transactions on Acoustics, Speech, and Signal Processing, Vol.36,NO.7,July1988
M. Ghuwar, W. Skarbek, âRecognition of Arabic Characters - A Survey,â Polish Academy of Science, Manuscript no. 740, Warsaw 1994.
N. Ström and others, "Acoustic Modelling Improvements in a Segment-Based Speech Recognizer," Proc. of the 1999 IEEE Workshop on Automatic Speech Recognition and Understanding,Keystone, Colorado, USA.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Saeed, K., DardziĆska, A. (2001). Cursive Letters Language Processing: Muqla Model and Toeplitz Matrices Approach. In: Larsen, H.L., Andreasen, T., Christiansen, H., Kacprzyk, J., ZadroĆŒny, S. (eds) Flexible Query Answering Systems. Advances in Soft Computing, vol 7. Physica, Heidelberg. https://doi.org/10.1007/978-3-7908-1834-5_30
Download citation
DOI: https://doi.org/10.1007/978-3-7908-1834-5_30
Publisher Name: Physica, Heidelberg
Print ISBN: 978-3-7908-1347-0
Online ISBN: 978-3-7908-1834-5
eBook Packages: Springer Book Archive