HANDWRITTEN SCRIPT AND WORD RECOGNITION – A VIEW-BASED APPROACH
DOI:
https://doi.org/10.47839/ijc.5.3.413Keywords:
Character recognition, word recognition without segmentation, minimal eigenvalues of Toeplitz matrices, neural networksAbstract
This paper presents a hybrid system for character and word recognition. It is based on a modification to the view-based approach presented in authors’ previous works. The algorithm is appropriate for dealing with whole, unsegmented words or isolated characters. The characteristic vectors taken from views of the tested image are processed with the method of minimal eigenvalues of Toeplitz matrices. The obtained series of minimal eigenvalues are used for classification with Artificial Neural Networks. The results of the experiments on different sets of words and letters are presented.References
K. Saeed. M. Tabedzki. M. Adamski. A New Approach for Object-Feature Extract and Recognition. 9th International Conference on Advanced Computer Systems – ACS’02. Miedzyzdroje, 23-25 October 2002. pp. 389-397.
K. Saeed, M. Tabedzki. Hybrid System for Letter Recognition. 3rd International Conference on Neural Networks and Artificial Intelligence – ICNNAI'03. Minsk, 2003. pp. 44-48.
K. Saeed, M. Tabedzki. A New Hybrid System for Recognition of Handwritten-Script. COMPUTING - International Scientific Journal of Computing. Institute of Computer Information Technologies, Volume 3, Issue 1, pp. 50-57, Ternopil 2004.
M. Tabedzki, K. Saeed. View-Based Word Recognition System. Proc. 4th Intern. Conf. on Neural Networks and Artificial Intelligence – ICNNAI'06. Brest, Belarus, 2006, pp. 145-148
M. Tabedzki, K. Saeed. A View-Based Toeplitz-Matrix-Supported System for Word Recognition without Segmentation. Proc. 6th Intern. Conf. on Intelligent System Design and Applications – ISDA'06. Jinan, Shandong, China, 2006. (Best Paper Award)
M. Tabedzki, K. Saeed. Hybrid Word Recognition System. Proc. 13th Intern. MultiConf. on Advanced Computer Systems - ACS-AIBITS/CISIM'06. Miedzyzdroje, Poland, 2006.
S. Haykin. Neural Networks. A Comprehensive Foundation. Prentice Hall, New Jersey, USA, second edition, 1999.
K. Saeed. On The Realization of Digital Filters. Proc. The 1st International Conference on Digital Signal Processing and its Applications – DSPA'98. Vol. 1, Moscow, 1998, pp. 141-143.
K. Saeed. A New Approach in Image Classification. Proc. 5th International Conference on Digital Signal Processing and its Applications – DSPA'03. Moscow 2003. Vol. 1, pp. 49-52.
G. Shakhnarovish, T. Darrell, and P. Indyk, Nearest-Neighbor Methods in Learning and Vision. The MIT Press, 2005.
A. N. Kolmogorov. On the Representation of Continuous Functions of Several Variables by Superposition of Continuous Functions of One Variable and Addition. Dokl. Akad. Nauk SSSR, 1957, vol. 114, pp. 953-956.
R. C. Gonzalez and R. E Woods. Digital Image Processing. Addison-Wesley Publishing Company. 1992. pp. 7-9, 413-414.
K. Bowyer and N. Ahuja. Advances in Image Understanding. IEEE Computer Society Press, 1996. p. 65.
K. Saeed, M. Nammous. A Simple Speech-and-Speaker Identification System. Accepted for publication in IEEE Trans. on Ind. Electronics – Humatronics. New York, USA, 2006.
J.J. De Oliveira Junior, J.M. De Carvalho, C.O.D.A Freitas, R. Sabourin. Evaluating NN and HMM Classifiers for Handwritten Word Recognition. Computer Graphics and Image Processing, Elect. Engg Dept., Fed. Univ. of Campina Grande, Brazil, 2002, pp. 210-217.
D. Guillevic, C.Y. Suen, HMM Word Recognition Engine. Fourth International Conference on Document Analysis and Recognition (ICDAR97). 1997, pp. 544-547.
V. Lavrenko, T.M. Rath, R. Manmatha, Holistic word recognition for handwritten historical documents. Document Image Analysis for Libraries. 2004, pp. 278-287.
Downloads
Published
How to Cite
Issue
Section
License
International Journal of Computing is an open access journal. Authors who publish with this journal agree to the following terms:• Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
• Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
• Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
