An effective segmentation method for single stroke online cursive Arabic words

A new method is used for character segmentation from cursive Arabic words. The method is based on statistical approach which uses Normalization and rectification, coordinate transformation and clustering to extract ligatures. The output is then filtered to extract start, overlapped and end segment errors. After applying the filter the characters are completely isolated and ready for recognition. The system, when testing the segmentation on 5 different Arabic sentences and by 20 different users, scored 98.03%, 94.82, 97.33 and 90% for normal segment, starting segment, last segment and overlapped segment.

[1]  Jihad El-Sana,et al.  Hierarchical On-line Arabic Handwriting Recognition , 2009, 2009 10th International Conference on Document Analysis and Recognition.

[2]  M. Hussain,et al.  Online Urdu Ligature Recognition using Spatial Temporal Neural Processing , 2005, 2005 Pakistan Section Multitopic Conference.

[3]  Adel M. Alimi,et al.  Arabic Handwriting Recognition Using Restored Stroke Chronology , 2009, 2009 10th International Conference on Document Analysis and Recognition.

[4]  Umi Kalthum Ngah,et al.  Normalization and rectification method for online hindi digit recognition with partial alignment algorithm , 2010, 2010 International Conference on Electronics and Information Engineering.

[5]  Adel M. Alimi,et al.  A new Approach for Online Arabic Handwriting Recognition , 2009 .

[6]  Anil K. Jain,et al.  Online script recognition , 2002, Object recognition supported by user interaction for service robots.

[7]  Khaled Daifallah,et al.  Recognition-Based Segmentation Algorithm for On-Line Arabic Handwriting , 2009, 2009 10th International Conference on Document Analysis and Recognition.

[8]  Fadi N. Sibai,et al.  Automatic processing of Arabic text , 2009, 2009 International Conference on Innovations in Information Technology (IIT).

[9]  Samia A. Mashali,et al.  Simultaneous Segmentation and Recognition of Arabic Characters in an Unconstrained On-Line Cursive Handwritten Document , 2007 .

[10]  Talaat S. El-Sheikh,et al.  Real-time arabic handwritten character recognition , 1989, Pattern Recognit..

[11]  Samir Al-Emami,et al.  On-Line Recognition of Handwritten Arabic Characters , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  K. Assaleh,et al.  Online Arabic handwriting recognition using continuous Gaussian mixture HMMS , 2007, 2007 International Conference on Intelligent and Advanced Systems.

[13]  B. Alsallakh,et al.  AraPen: An Arabic Online Handwriting Recognition System , 2006, 2006 2nd International Conference on Information & Communication Technologies.

[14]  A. M. Alimi,et al.  A neuro-fuzzy approach to recognize Arabic handwritten characters , 1997, Proceedings of International Conference on Neural Networks (ICNN'97).

[15]  Malcolm I. Heywood,et al.  Towards the on-line recognition of Arabic characters , 2002, Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290).