AUTHORS: Aissa Kerkour Elmiad, Azzedine Mazzroui
Download as PDF
ABSTRACT: We propose in this work an approach to segmentation of Arabic texts printed offline open vocabulary. The method is based on human perception using their natural power for segmentation. The novelty of our work is in the analysis of this type of approach on complex fonts and calligraphy has strong ligatures; we propose an artificial segmentation feature extraction based on the use of structural primitives for a robust description of the different morphological variability font considered. The proposed algorithm yielded results quite satisfactory with an extension for the resolution of a particular case of the sub-segmentation. This model has enabled us to increase significantly the recognition performance and develop a recognition system open vocabulary.
KEYWORDS: OCR Arabic, skeletonization, diacritics, ligatures, segmentation-recognition, multi-font
REFERENCES:
[1] K.M. Sayre, Machine recognition of handwritten words : A project report. Pattern Recognition, vol. 5, no. 3, pp. 213-228, septembre 1973.
[2] X. Dupre. Contributions à la reconnaissance de l’écriture cursive à l’aide de modèles de Markov cachés. PhD thesis, Univérsité de Rene Descartes - Paris V, 2003.
[3] E. Lecolinet. Planar markov modeling for arabic writing recognition : Advancement state. In Proceedings of the first IEEE Int. Conf. on Document Analysis and Recognition (ICDAR), pp. 740-748, Saint Malo, France, Sept. 1991.
[4] N. Essoukri Ben Amara, F. Bouslama. Classification of Arabic Script Using Multiple Sources of Information: State of the Art and Perspectives. Int. Journal on Document Analysis and Recognition, vol. 5, no. 4, pp. 195-212, 2003.
[5] S. Gazzah, N. Essoukri, Ben Amara. Utilisation des Ondelettes en Caractérisation des Fontes Arabes. Int. Conf. On Image and Signal Processing, ICISP’2003, Maroc, June 2003.
[6] R. G. Casey, E. Lecolinet, A Survey of Methods and Strategies in Character Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 18, pp. 690-706, 1996.
[7] A. Mazroui, A. Kerkour Elmiad, Recognition of multifont Isolated Arabic characters by Bézier Curves, International Journal of Computer Applications, vol. 100 - No. 6, 2014
[8] F. Menasri. Contributions à la reconnaissance de l’écriture Arabe manuscrite. PhD thesis, Université de Paris Descartes, 2008
[9] A.M. AL-Shatnawi, S. AL-Salaimeh, F. H. ALZawaideh, and O. Khairuddin, Offline Arabic Text Recognition-AnOverview, World of Computer Science and Information Technology Journal (WCSIT), vol. 1, no. 5, pp. 184-192, 2011.
[10] M. S. Khorsheed, Off-Line Arabic Character Recognition - A Review. Pattern Analysis & Applications vol. 5, no. 1, pp. 31-45, 2002.
[11] U.-V. Marti, H. Bunke, Using a statistical language model to improve the performance of an HMM-based cursive handwriting recognition systems, World Scientific Publishing Co., Inc., pp. 65-90, 2002.
[12] C.A.CRUZ, R.R.KUOPA, M.R.AYALA, A.A.GONZALEZ, R.E.PEREZ, 'High order statistical texture analysis-font recognition applied', Pattern Recognition Letters, vol 26, N° 2, 2005, pp 135-145.
[13] AdbulKader A., Two-tier approach for Arabic offline handwriting recognition. In The Tenth International Workshop on Frontiers in Handwriting Recognition (IWFHR 10). (2006).
[14] Iping Supriana, , Albadr Nasution, Arabic Character Recognition System Development, Vol 11, June 2013, p: 334–341, 4th International Conference on Electrical Engineering and Informatics, ICEEI 2013
[15] STARS Company, Arabic OCR, 2010
[16] Andrey Stolyarenko & Nachum Dershowitz. OCR for Arabic using SIFT Descriptors with Online Failure, , OCR for Arabic using SIFT Descriptors with Online ,2011 ISCOLא 'ט אייר התשע 'כ ,חמישי ,Failure Thursday, June 2, 2011.
