×

On-line arabic handwriting recognition with templates. (English) Zbl 1187.68504

Summary: After a long period of focus on western and East Asian scripts there is now a general trend in the on-line handwriting recognition community to explore recognition of other scripts such as Arabic and various Indic scripts. One difficulty with the Arabic script is the number and position of diacritic marks associated to Arabic characters. This paper explores the application of a template matching scheme to the recognition of Arabic script with a novel algorithm for dynamically treating the diacritical marks. Template based systems are robust to conditions with scarce training data and in experiments the proposed system outperformed a reference system based on the promising state-of-the-art network technique of BLSTM. Experiments have been conducted in an environment similar to that of many handheld devices with promising results both in terms of memory consumption and response time.

MSC:

68T10 Pattern recognition, speech recognition

Software:

NPen++
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Biadsy, F.; El-Sana, J.; Habash, N., Online Arabic handwriting recognition using hidden Markov models, (Proceedings of the Tenth International Workshop on Frontiers in Handwriting Recognition (2006)), 85-90
[2] Halavati, R.; Jamzad, M.; Soleymani, M., A novel approach to Persian online hand writing recognition, Transactions on Engineering, Computing and Technology, 6, 232-236 (2005)
[3] Liwicki, M.; Graves, A.; Bunke, H.; Schmidhuber, J., A novel approach to on-line handwriting recognition based on bidirectional long short-term memory networks, (ICDAR ’07: Proceedings of the Ninth International Conference on Document Analysis and Recognition (ICDAR 2007), vol. 1 (2007)), 367-371
[4] A. Graves, M. Liwicki, S. Fernandez, R. Bertolami, H. Bunke, J. Schmidhuber, Bidirectional long short-term memory networks for on-line handwriting recognition, IEEE Transactions on Pattern Analysis and Machine Intelligence (2008), to appear.; A. Graves, M. Liwicki, S. Fernandez, R. Bertolami, H. Bunke, J. Schmidhuber, Bidirectional long short-term memory networks for on-line handwriting recognition, IEEE Transactions on Pattern Analysis and Machine Intelligence (2008), to appear.
[5] M.-P. Schambach, J. Rottland, T. Alary, How to convert a Latin handwriting recognition system to Arabic, in: Proceedings of the ICFHR, 2008, pp. 265-270.; M.-P. Schambach, J. Rottland, T. Alary, How to convert a Latin handwriting recognition system to Arabic, in: Proceedings of the ICFHR, 2008, pp. 265-270.
[6] Schenk, J.; Rigoll, G., Novel hybrid nn/hmm modelling techniques for on-line handwriting recognition, (Proceedings of the Tenth International Workshop on Frontiers in Handwriting Recognition (2006)), 619-623
[7] Mitoma, H.; Uchida, S.; Sakoe, H., Online character recognition based on elastic matching and quadratic discrimination, (Proceedings of the Eighth International Conference on Document Analysis and Recognition (2005)), 36-40
[8] Sternby, J., An additive single character recognition method, (Proceedings of the Tenth International Workshop on Frontiers in Handwriting Recognition (2006)), 417-422
[9] Sternby, J.; Friberg, C., The recognition graph—language independent adaptable on-line cursive script recognition, (Proceedings of the Eighth International Conference on Document Analysis and Recognition (2005)), 14-18
[10] Jäger, S.; Manke, S.; Waibel, A., \( \operatorname{Npen} ++\): an on-line handwriting recognition system, (Proceedings of the Seventh International Workshop on Frontiers in Handwriting Recognition, Amsterdam, Netherlands (2000)), 249-260
[11] J. Sternby, Template based recognition of on-line handwriting, Ph.D. Thesis, Lund Institute of Technology, Centre for Mathematical Sciences, May 2008.; J. Sternby, Template based recognition of on-line handwriting, Ph.D. Thesis, Lund Institute of Technology, Centre for Mathematical Sciences, May 2008.
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.