Abstract
In recent years, machine learning algorithms have been replaced by deep learning in various fields such as computer vision, machine translation, natural language processing, and speech recognition. Deep learning methods in recent times have been extremely successful in developing optical character recognition systems. Deep learning methods can learn directly from raw data. Therefore, they can be perfectly applied for recognition of text from images. Notably, convolutional neural networks and recurrent neural networks are significantly employed for text recognition and word spotting. In this article, the most important techniques of deep learning used in the recognition Arabic-adapted scripts such as Urdu, Arabic, and Pashto have been summarized and compared.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ahmad I, Wang X, Mao Y, Liu G, Ahmad H, Ullah R (2017) Ligature based Urdu Nastaleeq sentence recognition using gated bidirectional long short term memory. Cluster Comput 21:703ā714
Ahmad I, Wang X, Li R, Ahmed M, Ullah R (2017) Line and ligature segmentation of Urdu Nastaleeq text. IEEE Access 5:10924ā10940. https://doi.org/10.1109/ACCESS.2017.2703155
Ahmad R, Afzal MZ, Rashid SF, Liwicki M, Breuel T (2015) Scale and rotation invariant OCR for Pashto cursive script using MDLSTM network, pp 1101ā1105. https://doi.org/10.1109/ICDAR.2015.7333931
Ahmad R, Afzal MZ, Rashid SF, Liwicki M, Breuel T, Dengel A (2016) Kpti: Katibās Pashto text imagebase and deep learning benchmark. https://doi.org/10.1109/ICFHR.2016.70
Ahmad R, Naz S, Afzal M, Rashid S, Liwicki M, Dengel A (2020) A deep learning based Arabic script recognition system: benchmark on KHAT. Int Arab J Inf Technol 17(3):299ā305. https://doi.org/10.34028/iajit/17/3/3
Ahmad R, Naz S, Afzal MZ, Amin S, Breuel T (2015) Robust optical recognition of cursive Pashto script using scale, rotation and location invariant approach. PLoS One 10:e0133648. https://doi.org/10.1371/journal.pone.0133648
Ahmad R, Naz S, Afzal MZ, Rashid SF (2020) A deep learning based Arabic script recognition system: benchmark on KHAT. Int Arab J Inf Technol 17:1ā6. https://doi.org/10.34028/iajit/17/3/3
Ahmed S, Naz S, Razzak M, Rashid SF, Afzal MZ, Breuel T (2015) Evaluation of cursive and non-cursive scripts using recurrent neural networks. Neural Comput Appl 27. https://doi.org/10.1007/s00521-015-1881-4
Ahmed S, Naz S, Swati S, Razzak M (2019) Handwritten Urdu character recognition using 1-dimensional BLSTM classifier. Neural Comput Appl 31. https://doi.org/10.1007/s00521-017-3146-x
Alonso E, Moysset B, Messina R (2019) Adversarial generation of handwritten text images conditioned on sequences
Chherawala Y, Roy P, Cheriet M (2013) Feature design for offline Arabic handwriting recognition: handcrafted vs automated?, pp 290ā294. https://doi.org/10.1109/ICDAR.2013.65
Ciresan D, Meier U, Schmidhuber J (2012) Transfer learning for Latin and Chinese characters with deep neural networks, ppĀ 1ā6. https://doi.org/10.1109/IJCNN.2012.6252544
Elleuch M, Maalej R (2016) A new design based-SVM of the CNN classifier architecture with dropout for offline Arabic handwritten recognition. Procedia Comput Sci 80:1712ā1723. https://doi.org/10.1016/j.procs.2016.05.512
Elleuch M, Tagougui N (2015). Deep learning for feature extraction of Arabic handwritten script. https://doi.org/10.1007/978-3-319-23117-4_32
Elleuch M, Tagougui N (2017) Optimization of DBN using regularization methods applied for recognizing Arabic handwritten script. Procedia Comput Sci 108:2292ā2297. https://doi.org/10.1016/j.procs.2017.05.070
Graves A, Schmidhuber J (2009) Offline handwriting recognition with multidimensional recurrent neural networks. In: Koller D, Schuurmans D, Bengio Y, Bottou L (eds) Advances in neural information processing systems, volĀ 21. Curran Associates, Inc. https://proceedings.neurips.cc/paper/2008/file/66368270ffd51418ec58bd793f2d9b1b-Paper.pdf
Gui L, Liang X, Chang X, Hauptmann AG (2019) Adaptive context-aware reinforced agent for handwritten text recognition. In: British machine vision conference 2018, BMVC 2018, pp 1ā13
Guo Y, Liu Y, Oerlemans A, Lao S, Wu S, Lew MS (2016) Deep learning for visual understanding: a review. Neurocomputing 187:27ā48. https://doi.org/10.1016/j.neucom.2015.09.116
Javed N, Shabbir S, Siddiqi I, Khurshid K (2017). Classification of Urdu ligatures using convolutional neural networksāa novel approach. https://doi.org/10.1109/FIT.2017.00024
Kassis M, Abdalhaleem A, Droby A, Alaasam R, El-Sana J (2017) VML-HD: the historical Arabic documents dataset for recognition systems. In: 2017 1st international workshop on Arabic script analysis and recognition (ASAR), pp 11ā14. https://doi.org/10.1109/ASAR.2017.8067751
Khamekhem S, Kessentini Y, Kanoun S (2019) Out of vocabulary word detection and recovery in Arabic handwritten text recognition. Pattern Recognit 93. https://doi.org/10.1016/j.patcog.2019.05.003
Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Pereira F, Burges CJC, Bottou L, Weinberger KQ (eds) Advances in neural information processing systems, volĀ 25. Curran Associates, Inc. https://proceedings.neurips.cc/paper/2012/file/c399862d3b9d6b76c8436e924a68c45b-Paper.pdf
Kumar A, Irsoy O, Ondruska P, Iyyer M, Bradbury J, Gulrajani I, Zhong V, Paulus R, Socher R (2016) Ask me anything: dynamic memory networks for natural language processing. In: Balcan MF, Weinberger KQ (eds) Proceedings of the 33rd international conference on machine learning. Proceedings of machine learning research, volĀ 48. PMLR, New York, New York, USA, pp 1378ā1387. http://proceedings.mlr.press/v48/kumar16.html
Lawgali A, Angelova M, Bouridane A (2013) HACDB: handwritten Arabic characters database for automatic character recognition, pp 255ā259
Lecun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436ā444. https://doi.org/10.1038/nature14539
Liu L, Ouyang W, Wang X, Fieguth P, Chen J, Liu X, PietikƤinen M (2020) Deep learning for generic object detection: a survey. Int J Comput Vis 128(2):261ā318. https://doi.org/10.1007/s11263-019-01247-4
Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: 2015 IEEE conference on computer vision and pattern recognition (CVPR), pp 3431ā3440. https://doi.org/10.1109/CVPR.2015.7298965
Maalej R (2016) Improving MDLSTM for offline Arabic handwriting recognition using dropout at different positions, pp 431ā438. https://doi.org/10.1007/978-3-319-44781-0_51
Mahmoud S, Ahmad I, Al-Khatib W, Alshayeb M, Parvez M, MƤrgner V, Fink G (2014) Khatt: an open Arabic offline handwritten text database. Pattern Recognit 47:1096ā1112. https://doi.org/10.1109/ICFHR.2012.224
MƤrgner V, El Abed H (2009) ICDAR 2009 Arabic handwriting recognition competition. In: Proceedings of the international conference on document analysis and recognition, ICDAR (Table 1), pp 1383ā1387. https://doi.org/10.1109/ICDAR.2009.256
Morillot O, Oprean C, Likforman-Sulem L, Mokbel C, Chammas E, Grosicki E (2013) The UOB-Telecom Paristech Arabic handwriting recognition and translation systems for the OpenHart 2013 competition
MƤrgner V, El Abed H (2009) ICDAR 2009 Arabic handwriting recognition competition. In: Proceedings of the international conference on document analysis and recognition, ICDAR (Table 1), pp 1383ā1387. https://doi.org/10.1109/ICDAR.2009.256
Naz S, Umar A, Ahmad R, Razzak M, Rashid SF, Shafait F (2016) Urdu Nastaāliq text recognition using implicit segmentation based on multi-dimensional long short term memory neural networks. SpringerPlus 5. https://doi.org/10.1186/s40064-016-3442-4
Naz S, Umar A, Ahmad R, Siddiqi I, Ahmed S, Razzak M, Shafait F (2017) Urdu Nastaliq recognition using convolutional-recursive deep learning. Neurocomputing 243. https://doi.org/10.1016/j.neucom.2017.02.081
Naz S, Umar AI, Ahmad R, Ahmed SB, Shirazi SH, Razzak MI (2017) Urdu Nastaāliq text recognition system based on multi-dimensional recurrent neural network and statistical features. Neural Comput Appl 28(2):219ā231. https://doi.org/10.1007/s00521-015-2051-4
Naz S, Umar AI, Ahmad R, Ahmed SB, Shirazi SH, Siddiqi I, Razzak MI (2016) Offline cursive Urdu-Nastaliq script recognition using multidimensional recurrent neural networks. Neurocomputing 177(C):228ā241. https://doi.org/10.1016/j.neucom.2015.11.030
Noh H, Hong S, Han B (2015) Learning deconvolution network for semantic segmentation. In: 2015 IEEE international conference on computer vision (ICCV), pp 1520ā1528. https://doi.org/10.1109/ICCV.2015.178
OāMahony N, Campbell S, Carvalho A, Harapanahalli S, Hernandez GV, Krpalkova L, Riordan D, Walsh J (2020) Deep learning vs. traditional computer vision. Advances in computer vision. Springer. https://doi.org/10.1007/978-3-030-17795-9_10
Pechwitz M, Snoussi S, MƤrgner V, Ellouze N, Amiri H (2002) IFN/ENIT-database of handwritten Arabic words
Poznanski A, Wolf L (2016) CNN-N-Gram for handwritingWord recognition, pp 2305ā2314. https://doi.org/10.1109/CVPR.2016.253
Rashid SF, Schambach MP, Rottland J, NĆ¼ll S (2013) Low resolution Arabic recognition with multidimensional recurrent neural networks. https://doi.org/10.1145/2505377.2505385
Razzak M, Husain A, Mirza A, Belad A (2012) Fuzzy based preprocessing using fusion of online and offline trait for online Urdu script based languages character recognition. Int J Innov Comput Inf Control 8
Ren JS, Xu L (2015) On vectorization of deep convolutional neural networks for vision tasks
Shrivastava A, Pfister T, Tuzel O, Susskind J, Wang W, Webb R (2017) Learning from simulated and unsupervised images through adversarial training
Simard P, Steinkraus D, Platt J (2003) Best practices for convolutional neural networks applied to visual document analysis, pp 958ā962. https://doi.org/10.1109/ICDAR.2003.1227801
Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition
Slimane F, Ingold R, Kanoun S, Alimi A, Hennebert J (2009) A new Arabic printed text image database and evaluation protocols, pp 946ā950. https://doi.org/10.1109/ICDAR.2009.155
Ul-Hasan A, Ahmed S, Rashid SF, Shafait F, Breuel T (2013) Offline printed Urdu Nastaleeq script recognition with bidirectional LSTM networks. https://doi.org/10.1109/ICDAR.2013.212
Vinod H (1976) Canonical ridge and econometrics of joint production. J Econom 4(2):147ā166. https://doi.org/10.1016/0304-4076(76)90010-5
Yousefi M, Soheili MR, Breuel T, Stricker D (2015) A comparison of 1d and 2d LSTM architectures for the recognition of handwritten Arabic. Proc SPIEāInt Soc Opt Eng 9402. https://doi.org/10.1117/12.2075930
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
Ā© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Bashir, M., Goyal, V., Giri, K.J. (2023). Deep Learning Architectures Applied onĀ Arabic-Adapted Scripts: A Review. In: Tiwari, S., Trivedi, M.C., Kolhe, M.L., Singh, B.K. (eds) Advances in Data and Information Sciences. Lecture Notes in Networks and Systems, vol 522. Springer, Singapore. https://doi.org/10.1007/978-981-19-5292-0_18
Download citation
DOI: https://doi.org/10.1007/978-981-19-5292-0_18
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-5291-3
Online ISBN: 978-981-19-5292-0
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)