Abstract

This paper presents an Arabic handwritten text recognition system for historical Manuscripts using the Matlab software, the paper is composed from number of stages, the first stage giving a short description of related work in handwritten Arabic recognition systems, the second stage discuss the preprocessing methods which contain of filtering, a certain methods will be applied on samples of database images todetect the best filter, normalization and cropping text for feature extraction, the third stage is the text segmentationinto lines, words, detecting the dots and remove it from the word with saving its position before segmentation to its primitives, the fourth stage gives a practical approach to the character recognition using a proposed multimodal technique by applying three techniques of character recognition, artificial neural network, hiddenmarkov modeland alinear classifier, saving the result into an array choosing the mode of thedata stored in the array,finally giving some experimental results.

References

• Zaher Al Aghbari, Salama Brook, "HAH manuscripts: A holistic paradigm for classifying and retrieving historical arabic handwritten documents Original Research Article", Expert Systems with Applications, Volume 36, Issue 8, October 2009, Pages 10942-10951.
• Jin Chen, Daniel Lopresti, "Model-based ruling line detection in noisy handwritten documents", Pattern Recognition Letters, In Press, Corrected Proof, Available online 15 September 2012.
• Jun Tan, Jian-Huang Lai, Chang-Dong Wang, Wen-Xian Wang, Xiao-XiongZuo, "A new handwritten character segmentation method based on nonlinear clusteringNeurocomputing, Volume 89, 15 July 2012, Pages 213-219.
• . Ntirogiannis, B. Gatos, I. Pratikakis, "A combined approach for the binarization of handwritten document images", Pattern Recognition Letters, In Press, Corrected Proof, Available online 11 October 2012.
• HananAljuaid,Zulkifli Muhammad and Muhammad Sarfraz. "A Tool to Develop Arabic Handwriting Recognition System Using Genetic Approach"(Journal of Computer Science 6 (5): 496-501, 2010 ISSN 1549-3636 © 2010 Science Publications).
• Gheith A. Abandah, Khaled S. Younis and Mohammed Z. Khedher "Handwriting Arabic Character RecognitionUsingMultiple Classifiers Based On Letter Form "Fifth IASTED International Conference on Signal Processing, Pattern Recognition and ApplicationsPages 128-133 ACTA Press Anaheim, CA, USA ©2008.
• WafaBoussellaa, AbderrazakZahour, Haikal El Abed, AbdellatifBenAbdelhafid, Adel M. Alimi: Unsupervised Block Covering Analysis for Text-Line Segmentation of Arabic Ancient Handwritten Document Images. ICPR 2010: 1929-1932.
• Ahmad M. Sarhan, and Omar I. Al Helalat"Arabic Character Recognition using Artificial Neural Networks and Statistical Analysis"Proceedings of World Academy of Science, Engineering and Technology Volume 21 May 2007 ISSN 1307-6884.
• VolkerMärgner – Haikal El Abed – Mario Pechwitz. "OfflineHandwritten ArabicWord Recognition Using HMM - a Character Based Approach without Explicit Segmentation "Eighth International Conference on Document Analysis and Recognition (ICDAR 2005), 29 August - 1 September 2005, Seoul, Korea.
• Holger R. Roth "ADAPTIVE FILTERS"17thMarch 2008.
• PietroPerona and Jitendra Malik1990 "Scale-space and edge detection using anisotropic diffusion"IEEE Transactions on Pattern Analysis and Machine Intelligence, 12 (7): 629–639.
• N. Ray and B. Saha, "Edge sensitive variational image thresholding," proceeding of: Image Processing, 2007. IEEE International Conference on, Volume: 6.
• M. Sezgin and B. Sankur (2003). "Survey over image thresholding techniques and quantitative performance evaluation". Journal of Electronic Imaging 13 (1): 146–165.
• J. Sauvola and M. Pietikainen, "Adaptivedocument image binarization," Pattern Recognition 33(2),pp. 225–236, 2000.
• I. A. Ismail, M. S. Farag 2006. " Advanced Neural-Network Training Algorithm with Optimized Error Based on Modified Gram Schmidt with reorthogonalization", International Journal of Intelligent Computing and Informational Sciences, Vol. 6, pp 69-74.
• Chaivatna Sumetphong, Supachai Tangwongsan 2006 "Modeling broken characters recognition as a set-partitioning problem", Pattern Recognition Letters, Volume 33, Issue 16, 1 December 2012, Pages 2270-2279.