Abstract
The success of using Hidden Markov Models (HMMs) for speech recognition application has motivated the adoption of these models for handwriting recognition especially the online handwriting that has large similarity with the speech signal as a sequential process. Some languages such as Arabic, Farsi and Urdo include large number of delayed strokes that are written above or below most letters and usually written delayed in time. These delayed strokes represent a modeling challenge for the conventional left-right HMM that is commonly used for Automatic Speech Recognition (ASR) systems. In this paper, we introduce a new approach for handling delayed strokes in Arabic online handwriting recognition using HMMs. We also show that several modeling approaches such as context based tri-grapheme models, speaker adaptive training and discriminative training that are currently used in most state-of-the-art ASR systems can provide similar performance improvement for Hand Writing Recognition (HWR) systems. Finally, we show that using a multi-pass decoder that use the computationally less expensive models in the early passes can provide an Arabic large vocabulary HWR system with practical decoding time. We evaluated the performance of our proposed Arabic HWR system using two databases of small and large lexicons. For the small lexicon data set, our system achieved competing results compared to the best reported state-of-the-art Arabic HWR systems. For the large lexicon, our system achieved promising results (accuracy and time) for a vocabulary size of 64k words with the possibility of adapting the models for specific writers to get even better results.
Similar content being viewed by others
References
El-Wakil MS, Shoukry AA (1989) On-line recognition of handwritten isolated arabic characters. Pattern Recogn 22(2):97–105
Kharma NN, Ward RK (2001) A novel invariant mapping applied to hand-written arabic character recognition. Pattern Recogn 34(11):2115–2120
Ahmad T, Taani Al (2005) An efficient feature extraction algorithm for the recognition of handwritten arabic digits. Int J Comput Intell 2(2):107–111
Almuallim H, Yamaguchi S (1987) A method of recognition of arabic cursive handwriting. Pattern Anal Mach Intell IEEE Trans 5:715–722
Elanwar RI, Rashwan MA, Mashali (2007) Simultaneous segmentation and recognition of arabic characters in an unconstrained on-line cursive handwritten document. In: Proceedings of world academy of science, engineering and technology, vol 23, pp 288–291
Daifallah K, Zarka N, Jamous H (2009) Recognition-based segmentation algorithm for on-line arabic handwriting. Document analysis and recognition, 2009. ICDAR’09, 10th international conference on, pp 886–890
Khorsheed MS (2003) Recognising handwritten arabic manuscripts using a single hidden markov model. Pattern Recogn Lett 24(14):2235–2242
Abdelazeem S, Eraqi HM (2011) On-line arabic handwritten personal names recognition system based on hmm. In Document analysis and recognition (ICDAR), 2011 international conference on, pp 1304–1308. IEEE, 2011
Ha J, Oh S, Kim J, Kwon Y (1993) Unconstrained handwritten word recognition with interconnected hidden markov models. IAPR, Buffalo, In: Third international workshop on frontiers in handwriting recognition
Razavi SM, Kabir E (2006) A simple method for online farsi subword recognition. J Electric Comput Eng (in Farsi) 2:63–72
Ghods V, Kabir E, Razzazi F (2013) Effect of delayed strokes on the recognition of online farsi handwriting. Pattern Recogn Lett 34(5):486–491
Ghods V, Kabir E (2011) Lexicon reduction using delayed strokes for the recognition of online farsi subwords. In: Proceedings of the 3rd international conference on computer engineering and technology (ICCET), 2011
Hu J, SG Lim, MK Brown(2000) Writer independent on-line handwriting recognition using an hmm approach. Pattern Recogn 33(1):133–147
Starner T, Makhoul J, Schwartz R, Chou G (1994) On-line cursive handwriting recognition using speech recognition methods. In Acoustics, speech, and signal processing, 1994. ICASSP-94, 1994 IEEE international conference on, pp V–125
Biadsy F, El-Sana J, Habash NY (2006) Online arabic handwriting recognition using hidden markov models. In: Proceedings of the 10th international workshop on frontiers of handwriting and recognition, 2006
Huang BQ, Zhang YB, Kechadi MT (2007) Preprocessing techniques for online handwriting recognition. In: Proceedings of the seventh international conference on intelligent systems design and applications, pp 793–800
Wulandhari LA, Haron H (2008) The evolution and trend of chain code scheme. ICGST Int J Graph Vision Image Process 8(3):17–23
Jaeger S, Manke S, Reichert J, Waibel A (2001) Online handwriting recognition: the npen++ recognizer. Int J Doc Anal Recogn 3(3):169–180
Julian F, Javier O-G (2008) Advances in biometrics. Springer, London
Anastasakos T, McDonough J, Schwartz R, Makhoul J (1996) A compact model for speaker-adaptive training. In Spoken language, 1996. ICSLP 96. Proceedings, fourth international conference on, vol 2, pp 1137–1140
Young S, Evermann G, Gales M, Hain T, Kershaw D, Liu X, Moore G, Odell J, Ollason D, Povey D et al. (1997) The HTK book, vol 2. Entropic Cambridge Research Laboratory Cambridge, Cambridge
Zhou D, He Y (2009) Discriminative training of the hidden vector state model for semantic parsing. Knowl Data Eng IEEE Trans 21(1):66–77
Gales MJF (2001) Adaptive training for robust asr. In Automatic speech recognition and understanding, 2001. ASRU’01. IEEE Workshop on, pp 15–20
Aljazeera.net. http://Aljazeera.net
SRILM - The SRI language modeling toolkit. http://www.speech.sri.com/projects/srilm
Kneser R, Ney H (1995) Improved backing-off for m-gram language modeling. In Acoustics, speech, and signal processing, 1995. ICASSP-95, 1995 international conference on, vol 1, pp 181–184. IEEE, 1995
El Abed H, Kherallah M, Märgner V, Alimi AM (2011) On-line arabic handwriting recognition competition. Int J Doc Anal Recogn (IJDAR) 14(1):15–23
Abdelaziz I, Altecondb AS (2014) A large-vocabulary arabic online handwriting recognition database. In To Be Submitted, 2014
Acknowledgments
Dr. Hassanin likes to acknowledge the National Plan for Science, Technology and Innovation (MAARIFAH), King Abdulaziz City for Science and Technology, Kingdom of Saudi Arabia– award number (11-INF-1997-03). He also acknowledges and thank the Science and Technology Unit, King Abdulaziz University for their support.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Abdelaziz, I., Abdou, S. & Al-Barhamtoshy, H. A large vocabulary system for Arabic online handwriting recognition. Pattern Anal Applic 19, 1129–1141 (2016). https://doi.org/10.1007/s10044-015-0526-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10044-015-0526-7