Machine Learning Approach for Arabic Handwritten Recognition
Source abstract
Abstract
Text recognition is an important area of the pattern recognition field. Natural language processing (NLP) and pattern recognition have been utilized efficiently in script recognition. Much research has been conducted on handwritten script recognition. However, the research on the Arabic language for handwritten text recognition received little attention compared with other languages. Therefore, it is crucial to develop a new model that can recognize Arabic handwritten text. Most of the existing models used to acknowledge Arabic text are based on traditional machine learning techniques. Therefore, we implemented a new model using deep machine learning techniques by integrating two deep neural networks. In the new model, the architecture of the Residual Network (ResNet) model is used to extract features from raw images. Then, the Bidirectional Long Short-Term Memory (BiLSTM) and connectionist temporal classification (CTC) are used for sequence modeling. Our system improved the recognition rate of Arabic handwritten text compared to other models of a similar type with a character error rate of 13.2% and word error rate of 27.31%. In conclusion, the domain of Arabic handwritten recognition is advancing swiftly with the use of sophisticated deep learning methods.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Handwritten Text Recognition Techniques · Image Processing and 3D Reconstruction · Vehicle License Plate Recognition
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Computer Engineering, College of Engineering and Petroleum, Kuwait University, Safat 13060, Kuwait
Computer Sciences Department, University of Hamburg, 22527 Hamburg, Germany
References (67)
Show source-provided references
1. Chaudhuri, A., Mandaviya, K., Badelia, P., and Ghosh, S.K. (2017). Optical Character Recognition Systems. Optical Character Recognition Systems for Different Languages with Soft Computing, Springer International Publishing.10.1007/978-3-319-50252-6 ↗
2. Eberhard, D.M., Simons, G.F., and Fennig, C.D. (2019). Gujarati. Ethnologue: Languages of the World, SIL Internationa. [22nd ed.].
3. Handwritten numeric and alphabetic character recognition and signature verification using neural network
4. Arabic character recognition system: A statistical approach for recognizing cursive typewritten text10.1016/0031-3203(90)90069-W ↗
5. Faizullah, S., Ayub, M.S., Hussain, S., and Khan, M.A. (2023). A Survey of OCR in Arabic Language: Applications, Techniques, and Challenges. Appl. Sci., 13.10.3390/app13074584 ↗
6. Recent advances of ML and DL approaches for Arabic handwriting recognition: A review
7. AlKhateeb, J.H., Jiang, J., Ren, J., and Ipson, S. (2009). Component-based segmentation of words from handwritten Arabic text. Int. J. Comput. Syst. Sci. Eng., 5.
8. Nashwan, F., Rashwan, M.A., Al-Barhamtoshy, H.M., Abdou, S.M., and Moussa, A.M. (2018). A holistic technique for an Arabic OCR system. J. Imaging, 4.10.3390/jimaging4010006 ↗
9. Investigation on deep learning for off-line handwritten Arabic character recognition10.1016/j.cogsys.2017.11.002 ↗
10. Arabic Handwritten Recognition Using Deep Learning: A Survey10.1007/s13369-021-06363-3 ↗
11. Hybrid Arabic handwritten character segmentation using CNN and graph theory algorithm
12. ADOCRNet: A Deep Learning OCR for Arabic Documents Recognition10.1109/ACCESS.2024.3379530 ↗
13. Deep Learning Algorithms for Arabic Optical Character Recognition: A Survey10.61356/j.mawa.2024.26861 ↗
14. Contribution to the Authenticity of Digitized Handwritten Signatures Through Deep Learning with Resnet-50 and Ocr10.26662/ijiert.v11i3.pp20-25 ↗
15. Kayabas, A., Topcu, A.E., and Kiliç, Ö. (2021, January 9–10). OCR Error Correction Using BiLSTM. Proceedings of the 2021 International Conference on Electrical, Computer and Energy Technologies (ICECET), Cape Town, South Africa.10.1109/ICECET52533.2021.9698712 ↗
16. A data-driven approach to RUL prediction of tools10.1007/s40436-023-00464-y ↗
17. Graves, A. (2012). Connectionist Temporal Classification. Supervised Sequence Labelling with Recurrent Neural Networks, Springer.10.1007/978-3-642-24797-2 ↗
18. He, Y. (2020, January 27–29). Research on Text Detection and Recognition Based on OCR Recognition Technology. Proceedings of the 2020 IEEE 3rd International Conference on Information Systems and Computer Aided Education (ICISCAE), Dalian, China.10.1109/ICISCAE51034.2020.9236870 ↗
19. Mahmoud, S.A., Ahmad, I., Alshayeb, M., Al-Khatib, W.G., Parvez, M.T., Fink, G.A., Märgner, V., and El Abed, H. (2012, January 18–20). Khatt: Arabic offline handwritten text database. Proceedings of the 2012 International Conference on Frontiers in Handwriting Recognition, Bari, Italy.10.1109/ICFHR.2012.224 ↗
20. Mezghani, A., Kanoun, S., Khemakhem, M., and El Abed, H. (2012, January 18–20). A database for arabic handwritten text image recognition and writer identification. Proceedings of the 2012 International Conference on Frontiers in Handwriting Recognition, Bari, Italy.10.1109/ICFHR.2012.155 ↗
21. An Effective Combination of Convolutional Neural Network and Support Vector Machine Classifier for Arabic Handwritten Recognition10.3103/S0146411623030069 ↗
22. Handwritten Arabic Character Recognition for Children Writing Using Convolutional Neural Network and Stroke Identification10.1007/s44230-023-00024-4 ↗
23. A new design based-SVM of the CNN classifier architecture with dropout for offline Arabic handwritten recognition10.1016/j.procs.2016.05.512 ↗
24. Jemni, S.K., Kessentini, Y., Kanoun, S., and Ogier, J.-M. (2018, January 24–27). Offline Arabic handwriting recognition using BLSTMs combination. Proceedings of the 2018 13th IAPR International Workshop on Document Analysis Systems (DAS), Vienna, Austria.10.1109/DAS.2018.54 ↗
25. BenZeghiba, M.F., Louradour, J., and Kermorvant, C. (2015, January 23–26). Hybrid word/Part-of-Arabic-Word Language Models for arabic text document recognition. Proceedings of the 2015 13th International Conference on Document Analysis and Recognition (ICDAR), Tunis, Tunisia.10.1109/ICDAR.2015.7333846 ↗
26. The viterbi algorithm10.1109/PROC.1973.9030 ↗
27. Stahlberg, F., and Vogel, S. (2015, January 7–11). The qcri recognition system for handwritten arabic. Proceedings of the International Conference on Image Analysis and Processing, Genoa, Italy.10.1007/978-3-319-23234-8_26 ↗
28. Povey, D., Zhang, X., and Khudanpur, S. (2014). Parallel training of deep neural networks with natural gradient and parameter averaging. arXiv.
29. Wigington, C., Stewart, S., Davis, B.L., Barrett, W.A., Price, B.L., and Cohen, S.D. (2017, January 9–15). Data Augmentation for Recognition of Handwritten Words and Lines Using a CNN-LSTM Network. Proceedings of the 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), Kyoto, Japan.10.1109/ICDAR.2017.110 ↗
30. Arabic handwriting recognition system using convolutional neural network10.1007/s00521-020-05070-8 ↗
31. CNN-based Methods for Offline Arabic Handwriting Recognition: A Review10.1007/s11063-024-11544-w ↗
32. DeepAHR: A deep neural network approach for recognizing Arabic handwritten recognition10.1007/s00521-024-09674-2 ↗
33. Optimised CNN Architectures for Handwritten Arabic Character Recognition
34. A transformer-based approach for Arabic offline handwritten text recognition10.1007/s11760-023-02970-9 ↗
35. KHATT: An open Arabic offline handwritten text database10.1016/j.patcog.2013.08.009 ↗
36. Ahmad, R., Naz, S., Afzal, M.Z., Rashid, S.F., Liwicki, M., and Dengel, A. (2017, January 9–15). Khatt: A deep learning benchmark on arabic script. Proceedings of the 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), Kyoto, Japan.10.1109/ICDAR.2017.358 ↗
37. Noise types and various removal techniques
38. Soille, P. (2013). Morphological Image Analysis: Principles and Applications, Springer Science & Business Media.
39. Stahlberg, F., and Vogel, S. (2015, January 23–26). Detecting dense foreground stripes in Arabic handwriting for accurate baseline positioning. Proceedings of the 2015 13th International Conference on Document Analysis and Recognition (ICDAR), Tunis, Tunisia.10.1109/ICDAR.2015.7333784 ↗
40. Statistical geometric components of straight lines (SGCSL) feature extraction method for offline Arabic/Persian handwritten words recognition10.1049/iet-ipr.2017.0839 ↗
41. Combining slanted-frame classifiers for improved HMM-based Arabic handwriting recognition10.1109/TPAMI.2008.136 ↗
42. Using features of local densities, statistics and HMM toolkit (HTK) for offline Arabic handwriting text recognition10.1016/j.jesit.2016.07.005 ↗
43. Jayech, K., Mahjoub, M.A., and Amara, N.E.B. (2015, January 22–24). Arabic handwriting recognition based on synchronous multi-stream HMM without explicit segmentation. Proceedings of the International Conference on Hybrid Artificial Intelligence Systems, Bilbao, Spain.10.1007/978-3-319-19644-2_12 ↗
44. Semi-continuous HMMs with explicit state duration for unconstrained Arabic word modeling and recognition10.1016/j.patrec.2008.05.008 ↗
45. Almodfer, R., Xiong, S., Mudhsh, M., and Duan, P. (2017, January 11–14). Multi-column deep neural network for offline Arabic handwriting recognition. Proceedings of the International Conference on Artificial Neural Networks, Alghero, Italy.10.1007/978-3-319-68612-7_30 ↗
46. Object detection with deep learning: A review10.1109/TNNLS.2018.2876865 ↗
47. Zeiler, M.D., and Fergus, R. (2014, January 6–12). Visualizing and understanding convolutional networks. Proceedings of the European Conference on Computer Vision, Zurich, Switzerland.10.1007/978-3-319-10590-1_53 ↗
48. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
49. Imagenet classification with deep convolutional neural networks
50. Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv.
51. Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., and Rabinovich, A. (2015, January 7–12). Going deeper with convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.10.1109/CVPR.2015.7298594 ↗
52. Learning long-term dependencies with gradient descent is difficult10.1109/72.279181 ↗
53. Glorot, X., and Bengio, Y. (2010, January 13–15). Understanding the difficulty of training deep feedforward neural networks. Proceedings of the 13th International Conferenceon Artificial Intelligence and Statistics (AISTATS), Chia Laguna Resort, Sardinia, Italy.
54. Cheng, Z., Bai, F., Xu, Y., Zheng, G., Pu, S., and Zhou, S. (2017, January 22–29). Focusing attention: Towards accurate text recognition in natural images. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.10.1109/ICCV.2017.543 ↗
55. Framewise phoneme classification with bidirectional LSTM and other neural network architectures10.1016/j.neunet.2005.06.042 ↗
56. Graves, A., Jaitly, N., and Mohamed, A.-r. (2013, January 8–12). Hybrid speech recognition with deep bidirectional LSTM. Proceedings of the 2013 IEEE Workshop on Automatic Speech Recognition and Understanding, Olomouc, Czech Republic.10.1109/ASRU.2013.6707742 ↗
57. Wang, A., Singh, A., Michael, J., Hill, F., Levy, O., and Bowman, S.R. (2018). GLUE: A multi-task benchmark and analysis platform for natural language understanding. arXiv.10.18653/v1/W18-5446 ↗
58. McCann, B., Bradbury, J., Xiong, C., and Socher, R. (2017). Learned in translation: Contextualized word vectors. arXiv.
59. Improving sentiment analysis via sentence type classification using BiLSTM-CRF and CNN10.1016/j.eswa.2016.10.065 ↗
60. Graves, A., Mohamed, A.-r., and Hinton, G. (2013, January 26–31). Speech recognition with deep recurrent neural networks. Proceedings of the 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, Vancouver, BC, Canada.10.1109/ICASSP.2013.6638947 ↗
61. Graves, A., Fernández, S., Gomez, F., and Schmidhuber, J. (2006, January 29). Connectionist temporal classification: Labelling unsegmented sequence data with recurrent neural networks. Proceedings of the 23rd International Conference on Machine Learning, New York, NY, USA.10.1145/1143844.1143891 ↗
62. An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition10.1109/TPAMI.2016.2646371 ↗
63. Heafield, K. (2011, January 30–31). KenLM: Faster and smaller language model queries. Proceedings of the Sixth Workshop on Statistical Machine Translation, Edinburgh, UK.
64. Stolcke, A., Zheng, J., Wang, W., and Abrash, V. (2011, January 11–15). SRILM at sixteen: Update and outlook. Proceedings of the IEEE Automatic Speech Recognition and Understanding Workshop, Waikoloa, HI, USA.
65. Federico, M., Bertoldi, N., and Cettolo, M. (2008). IRSTLM: An open source toolkit for handling large scale language models. Interspeech, 1618–1621.10.21437/Interspeech.2008-271 ↗
66. Zeghiba, M.F.B. (2017, January 3–5). Arabic word decomposition techniques for offline Arabic text transcription. Proceedings of the 2017 1st International Workshop on Arabic Script Analysis and Recognition (ASAR), Nancy, France.10.1109/ASAR.2017.8067755 ↗
67. Out of vocabulary word detection and recovery in Arabic handwritten text recognition10.1016/j.patcog.2019.05.003 ↗