A Survey of OCR in Arabic Language: Applications, Techniques, and Challenges
Source abstract
Abstract
Optical character recognition (OCR) is the process of extracting handwritten or printed text from a scanned or printed image and converting it to a machine-readable form for further data processing, such as searching or editing. Automatic text extraction using OCR helps to digitize documents for improved productivity and accessibility and for preservation of historical documents. This paper provides a survey of the current state-of-the-art applications, techniques, and challenges in Arabic OCR. We present the existing methods for each step of the complete OCR process to identify the best-performing approach for improved results. This paper follows the keyword-search method for reviewing the articles related to Arabic OCR, including the backward and forward citations of the article. In addition to state-of-art techniques, this paper identifies research gaps and presents future directions for Arabic OCR.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Handwritten Text Recognition Techniques · Image Retrieval and Classification Techniques · Vehicle License Plate Recognition
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Computer Science, Islamic University, Madinah 42351, Saudi Arabia
Department of Computer Science, Lahore University of Management Sciences, Lahore 54792, Pakistan
Department of Telecommunication, Hazara University, Mansehra 21120, Pakistan
Funding
Deputyship of Research & Innovation, Ministry of Education, Saudi Arabia
References (100+)
Show source-provided references
1. A survey on the existing arabic optical character recognition and future trends
2. Beg, A., Ahmed, F., and Campbell, P. (2010, January 28–30). Hybrid OCR techniques for cursive script languages-a review and applications. Proceedings of the International Conference on Computational Intelligence, Communication Systems and Networks, Liverpool, UK.10.1109/CICSyN.2010.36 ↗
3. A Survey on Arabic Handwritten Script Recognition Systems
4. Islam, N., Islam, Z., and Noor, N. (2017). A survey on optical character recognition system. arXiv.
5. Rashid, D., and Kumar Gondhi, N. (2022, January 21–23). Scrutinization of Urdu Handwritten Text Recognition with Machine Learning Approach. Proceedings of the International Conference on Emerging Technologies in Computer Engineering, Xiamen, China.10.1007/978-3-031-07012-9_33 ↗
6. Idrees, S., and Hassani, H. (2021). Exploiting Script Similarities to Compensate for the Large Amount of Data in Training Tesseract LSTM: Towards Kurdish OCR. Appl. Sci., 11.10.3390/app11209752 ↗
7. Bafjaish, S.S., Azmi, M.S., Al-Mhiqani, M.N., Radzid, A.R., and Mahdin, H. (2018). Skew detection and correction of Mushaf Al-Quran script using hough transform. Int. J. Adv. Comput. Sci. Appl., 9.10.14569/IJACSA.2018.090852 ↗
8. A survey of OCR applications10.7763/IJMLC.2012.V2.137 ↗
9. Antonio, J., Putra, A.R., Abdurrohman, H., and Tsalasa, M.S. (2022, January 29–30). A Survey on Scanned Receipts OCR and Information Extraction. Proceedings of the International Conference on Document Analysis and Recognit, Jerusalem, Israel.
10. A review of arabic text recognition dataset
11. Handwritten Urdu character recognition using one-dimensional BLSTM classifier10.1007/s00521-017-3146-x ↗
12. Zayene, O., Masmoudi Touj, S., Hennebert, J., Ingold, R., and Essoukri Ben Amara, N. (2018). Open datasets and tools for arabic text detection and recognition in news video frames. J. Imaging, 4.10.3390/jimaging4020032 ↗
13. QTID: Quran Text Image Dataset
14. Pechwitz, M., Maddouri, S.S., Märgner, V., Ellouze, N., and Amiri, H. (2002). IFN/ENIT-Database of Handwritten Arabic Words, CIFED.
15. Al-Ma’adeed, S., Elliman, D., and Higgins, C.A. (2002, January 6–8). A data base for Arabic handwritten text recognition research. Proceedings of the International workshop on frontiers in handwriting recognition, Niagara-on-the-Lake, ON, Canada.
16. Slimane, F., Ingold, R., Kanoun, S., Alimi, A.M., and Hennebert, J. (2009). Database and Evaluation Protocols for Arabic Printed Text Recognition, DIUF-University of Fribourg.
17. Lawgali, A., Angelova, M., and Bouridane, A. (2013, January 10–12). HACDB: Handwritten Arabic characters database for automatic character recognition. Proceedings of the European Workshop on Visual Information Processing (EUVIP), Paris, France.
18. Sabbour, N., and Shafait, F. (2005, January 16–20). A segmentation-free approach to Arabic and Urdu OCR. Proceedings of the Document Recognition and Retrieval, San Jose, CA, USA.
19. Saddami, K., Munadi, K., and Arnia, F. (2015, January 21–24). A database of printed Jawi character image. Proceedings of the International Conference on Image Information Processing (ICIIP), Waknaghat, India.10.1109/ICIIP.2015.7414740 ↗
20. KHATT: An open Arabic offline handwritten text database10.1016/j.patcog.2013.08.009 ↗
21. Yousfi, S., Berrani, S.A., and Garcia, C. (2015, January 23–26). ALIF: A dataset for Arabic embedded text recognition in TV broadcast. Proceedings of the International Conference on Document Analysis and Recognition (ICDAR), Tunis, Tunisia.10.1109/ICDAR.2015.7333958 ↗
22. Zayene, O., Hennebert, J., Touj, S.M., Ingold, R., and Amara, N.E.B. (2015, January 23–26). A dataset for Arabic text detection, tracking and recognition in news videos-AcTiV. Proceedings of the International Conference on Document Analysis and Recognition (ICDAR), Tunis, Tunisia.10.1109/ICDAR.2015.7333911 ↗
23. Chabchoub, F., Kessentini, Y., Kanoun, S., Eglin, V., and Lebourgeois, F. (2016, January 4–7). SmartATID: A mobile captured Arabic Text Images Dataset for multi-purpose recognition tasks. Proceedings of the International Conference on Frontiers in Handwriting Recognition (ICFHR), Hyderabad, India.10.1109/ICFHR.2016.0034 ↗
24. Sulaiman, A., Omar, K., and Nasrudin, M.F. (2017, January 25–27). A database for degraded Arabic historical manuscripts. Proceedings of the International Conference on Electrical Engineering and Informatics (ICEEI), Langkawi, Malaysia.10.1109/ICEEI.2017.8312375 ↗
25. A Printed PAW Image Database of Arabic Language for Document Analysis and Recognition10.5614/itbj.ict.res.appl.2017.11.2.6 ↗
26. Databases for recognition of handwritten Arabic cheques10.1016/S0031-3203(02)00064-X ↗
27. A multiple feature/resolution scheme to Arabic (Indian) numerals recognition using hidden Markov models10.1016/j.sigpro.2008.12.022 ↗
28. Asiri, A.M., and Khorsheed, M.S. (2005, January 26–28). Automatic Processing of Handwritten Arabic Forms using Neural Networks. Proceedings of the IEC (Prague), Prague, Czech Republic.
29. KAFD Arabic font database10.1016/j.patcog.2013.12.012 ↗
30. Arabic handwriting data base for text recognition10.1016/j.protcy.2013.12.231 ↗
31. ARABASE: A Relational Database for Arabic OCR Systems
32. Srihari, S., Srinivasan, H., Babu, P., and Bhole, C. (2005, January 2–4). Handwritten arabic word spotting using the cedarabic document analysis system. Proceedings of the Symposium on Document Image Understanding Technology (SDIUT-05), College Park, MD, USA.
33. Urdu character recognition: A systematic literature review10.1504/IJAPR.2021.118914 ↗
34. Urdu optical character recognition systems: Present contributions and future directions10.1109/ACCESS.2018.2865532 ↗
35. Bhatti, A., Arif, A., Khalid, W., Khan, B., Ali, A., Khalid, S., and Rehman, A.u. (2023). Recognition and Classification of Handwritten Urdu Numerals Using Deep Learning Techniques. Appl. Sci., 13.10.3390/app13031624 ↗
36. Khosrobeigi, Z., Veisi, H., Hoseinzade, E., and Shabanian, H. (2022). Persian Optical Character Recognition Using Deep Bidirectional Long Short-Term Memory. Appl. Sci., 12.10.3390/app122211760 ↗
37. Urdu handwritten text recognition: A survey10.1049/iet-ipr.2019.0401 ↗
38. The optical character recognition of Urdu-like cursive scripts10.1016/j.patcog.2013.09.037 ↗
39. Printed Arabic script recognition: A survey
40. Osman, H., Zaghw, K., Hazem, M., and Elsehely, S. (2020). An Efficient Language-Independent Multi-Font OCR for Arabic Script. arXiv.10.5121/csit.2020.101506 ↗
41. Muhammad, M., and ElGhazaly, T. (2013, January 27–30). Handling OCR-degraded arabic text: A comprehensive survey. Proceedings of the ISSR Conference, Turku, Finland.
42. Dinges, L., Al-Hamadi, A., Elzobi, M., and El-Etriby, S. (2016). Synthesis of common Arabic handwritings to aid optical character recognition research. Sensors, 16.10.3390/s16030346 ↗
43. Bouressace, H. (2022, January 12–13). A Review of Arabic Document Analysis Methods. Proceedings of the International Conference on Pattern Analysis and Intelligent Systems (PAIS), Oum El Bouaghi, Algeria.10.1109/PAIS56586.2022.9946919 ↗
44. An efficient, font independent word and character segmentation algorithm for printed Arabic text
45. A Novel Approach to Printed Arabic Optical Character Recognition10.1007/s13369-021-06163-9 ↗
46. Majumdar, S., and Brick, A. (2022). Recognizing Handwriting Styles in a Historical Scanned Document Using Scikit-Fuzzy c-means Clustering. arXiv.
47. Mostafa, A., Mohamed, O., Ashraf, A., Elbehery, A., Jamal, S., Khoriba, G., and Ghoneim, A.S. (2021, January 26–27). OCFormer: A Transformer-Based Model For Arabic Handwritten Text Recognition. Proceedings of the International Mobile, Intelligent, and Ubiquitous Computing Conference (MIUCC), Cairo, Egypt.10.1109/MIUCC52538.2021.9447608 ↗
48. Quranic script optical text recognition using deep learning in IoT systems
49. Moudgil, A., Singh, S., and Gautam, V. (2022). Cyber Intelligence and Information Retrieval, Springer.
50. Huang, Z., Chen, K., He, J., Bai, X., Karatzas, D., Lu, S., and Jawahar, C. (2019, January 20–25). Icdar2019 competition on scanned receipt ocr and information extraction. Proceedings of the International Conference on Document Analysis and Recognition (ICDAR), Sydney, Australia.10.1109/ICDAR.2019.00244 ↗
51. Bashir, M.H., Azmi, A.M., Nawaz, H., Zaghouani, W., Diab, M., Al-Fuqaha, A., and Qadir, J. (2022). Arabic natural language processing for Qur’anic research: A systematic review. Artif. Intell. Rev.10.1007/s10462-022-10313-2 ↗
52. OCR binarization and image pre-processing for searching historical documents10.1016/j.patcog.2006.04.043 ↗
53. Michalak, H., and Okarma, K. (2020). Robust combined binarization method of non-uniformly illuminated document images for alphanumerical character recognition. Sensors, 20.10.3390/s20102914 ↗
54. Tellache, M., Sid-Ahmed, M., and Abaza, B. (1993, January 19–21). Thinning algorithms for Arabic OCR. Proceedings of the Pacific Rim Conference on Communications Computers and Signal Processing, Victoria, BC, Canada.
55. Mohsenzadegan, K., Tavakkoli, V., and Kyamakya, K. (2022). Deep Neural Network Concept for a Blind Enhancement of Document-Images in the Presence of Multiple Distortions. Appl. Sci., 12.10.3390/app12199601 ↗
56. Mahmud, J.U., Raihan, M.F., and Rahman, C.M. (2003, January 15–17). A complete OCR system for continuous Bengali characters. Proceedings of the Conference on Convergent Technologies for Asia-Pacific Region (TENCON), Bangalore, India.
57. Mohsenzadegan, K., Tavakkoli, V., and Kyamakya, K. (2022). A Smart Visual Sensing Concept Involving Deep Learning for a Robust Optical Character Recognition under Hard Real-World Conditions. Sensors, 22.10.3390/s22166025 ↗
58. Nashwan, F.M., Rashwan, M.A., Al-Barhamtoshy, H.M., Abdou, S.M., and Moussa, A.M. (2017). A holistic technique for an Arabic OCR system. J. Imaging, 4.10.3390/jimaging4010006 ↗
59. Steps involved in text recognition and recent research in OCR; a study
60. Skew detection and correction in document images based on straight-line fitting10.1016/S0167-8655(03)00010-2 ↗
61. Bao, W., Yang, C., Wen, S., Zeng, M., Guo, J., Zhong, J., and Xu, X. (2022). A Novel Adaptive Deskewing Algorithm for Document Images. Sensors, 22.10.3390/s22207944 ↗
62. Boiangiu, C.A., Dinu, O.A., Popescu, C., Constantin, N., and Petrescu, C. (2020). Voting-based document image skew detection. Appl. Sci., 10.10.3390/app10072236 ↗
63. Efficient skew detection and correction in scanned document images through clustering of probabilistic hough transforms10.1016/j.patrec.2021.09.014 ↗
64. Li, Y., Zou, F., Yang, S., Liu, H., Ding, Y., and Zhu, K. (2020, January 11–13). Research on Improving OCR Recognition Based on Bending Correction. Proceedings of the International Information Technology and Artificial Intelligence Conference (ITAIC), Chongqing, China.10.1109/ITAIC49862.2020.9339105 ↗
65. Schulter, S., Leistner, C., and Bischof, H. (2015, January 7–12). Fast and accurate image upscaling with super-resolution forests. Proceedings of the Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.10.1109/CVPR.2015.7299003 ↗
66. Pandey, R.K., Vignesh, K., and Ramakrishnan, A. (2018). Binary document image super resolution for improved readability and OCR performance. arXiv.
67. An approach to analysis of Arabic text documents into text lines, words, and characters
68. Segmentation techniques for recognition of Arabic-like scripts: A comprehensive survey10.1007/s10639-015-9377-5 ↗
69. Thorat, C., Bhat, A., Sawant, P., Bartakke, I., and Shirsath, S. (2022). A Detailed Review on Text Extraction Using Optical Character Recognition. ICT Anal. Appl., 719–728.10.1007/978-981-16-5655-2_69 ↗
70. Learning-free, divide and conquer text-line extraction algorithm for printed Arabic text with diacritics
71. An approach to a comprehensive test framework for analysis and evaluation of text line segmentation algorithms10.3390/s110908782 ↗
72. Basic test framework for the evaluation of text line segmentation and text parameter extraction10.3390/s100505263 ↗
73. Reisswig, C., Katti, A.R., Spinaci, M., and Höhne, J. (2019, January 14). Chargrid-OCR: End-to-end trainable optical character recognition through semantic segmentation and object detection. Proceedings of the Workshop on Document Intelligence at NeurIPS 2019, Vancouver, BC, Canada.
74. Agarwal, M., Hassan, F., Pandey, G., and Ghosh, S. (2021). Emerging Trends in Data Driven Computing and Communications: Proceedings of DDCIoT 2021, Springer.
75. Boualam, M., Elfakir, Y., Khaissidi, G., and Mrabti, M. (2020, January 14–16). Arabic handwriting word recognition based on convolutional recurrent neural network. Proceedings of the 6th International Conference on Wireless Technologies, Embedded, and Intelligent Systems (WITS 2020), Fez, Morocco.
76. Patil, S., Varadarajan, V., Mahadevkar, S., Athawade, R., Maheshwari, L., Kumbhare, S., Garg, Y., Dharrao, D., Kamat, P., and Kotecha, K. (2022). Enhancing Optical Character Recognition on Images with Mixed Text Using Semantic Segmentation. J. Sens. Actuator Netw., 11.10.3390/jsan11040063 ↗
77. Recognition of Visual Arabic Scripting News Ticker from Broadcast Stream10.1109/ACCESS.2022.3179366 ↗
78. A survey on Arabic character segmentation10.1007/s10032-012-0188-6 ↗
79. Characters Segmentation from Arabic Handwritten Document Images: Hybrid Approach
80. AbdAllah, N., and Viriri, S. (2021). Off-Line Arabic Handwritten Words Segmentation using Morphological Operators. arXiv.10.5121/sipij.2020.11602 ↗
81. Jabde, M., Patil, C., Mali, S., and Vibhute, A. (September, January 31). Comparative Study of Machine Learning and Deep Learning Classifiers on Handwritten Numeral Recognition. Proceedings of the International Symposium on Intelligent Informatics, Trivandrum, India.
82. A-survey of feature extraction and classification techniques in OCR systems
83. Hamida, S., El Gannour, O., Cherradi, B., Ouajji, H., and Raihani, A. (2022). Efficient feature descriptor selection for improved Arabic handwritten words recognition. Int. J. Electr. Comput. Eng., 12.10.11591/ijece.v12i5.pp5304-5312 ↗
84. Peng, X., Cao, H., Setlur, S., Govindaraju, V., and Natarajan, P. (2013, January 24). Multilingual OCR research and applications: An overview. Proceedings of the International Workshop on Multilingual OCR, Washington, DC, USA.10.1145/2505377.2509977 ↗
85. Bergamaschi, S., De Nardis, S., Martoglia, R., Ruozzi, F., Sala, L., Vanzini, M., and Vigliermo, R.A. (2022). Novel perspectives for the management of multilingual and multialphabetic heritages through automatic knowledge extraction: The digitalmaktaba approach. Sensors, 22.10.3390/s22113995 ↗
86. Attention-based CNN-RNN Arabic text recognition from natural scene images10.3390/forecast3030033 ↗
87. An Arabic Manuscript Regions Detection, Recognition and Its Applications for OCRing
88. Text recognition in the wild: A survey
89. Bouchakour, L., Meziani, F., Latrache, H., Ghribi, K., and Yahiaoui, M. (2021, January 21–22). Printed Arabic Characters Recognition Using Combined Features and CNN classifier. Proceedings of the International Conference on Recent Advances in Mathematics and Informatics (ICRAMI), Tebessa, Algeria.10.1109/ICRAMI52622.2021.9585941 ↗
90. Ahlawat, S., Choudhary, A., Nayyar, A., Singh, S., and Yoon, B. (2020). Improved handwritten digit recognition using convolutional neural networks (CNN). Sensors, 20.10.3390/s20123344 ↗
91. An Analysis of Optical Character Recognition (OCR) Methods10.6025/jcl/2019/10/3/81-91 ↗
92. Al-Sadawi, B., Hussain, A., and Ali, N.S. (2021, January 28–29). High-Performance Printed Arabic Optical Character Recognition System Using ANN Classifier. Proceedings of the Palestinian International Conference on Information and Communication Technology, Gaza, Palestine.10.1109/PICICT53635.2021.00013 ↗
93. Mittal, R., and Garg, A. (2020, January 15–17). Text extraction using OCR: A systematic review. Proceedings of the International Conference on Inventive Research in Computing Applications, Coimbatore, India.10.1109/ICIRCA48905.2020.9183326 ↗
94. Arabic handwritten recognition using deep learning: A survey10.1007/s13369-021-06363-3 ↗
95. Generative Adversarial Network for an Improved Arabic Handwritten Characters Recognition
96. A detailed analysis of optical character recognition technology10.18100/ijamec.270374 ↗
97. Subramani, N., Matton, A., Greaves, M., and Lam, A. (2020). A survey of deep learning approaches for ocr and document understanding. arXiv.
98. Survey of post-ocr processing approaches10.1145/3453476 ↗
99. Neto, A.F.d.S., Bezerra, B.L.D., and Toselli, A.H. (2020). Towards the natural language processing as spelling correction for offline handwritten text recognition systems. Appl. Sci., 10.10.3390/app10217711 ↗
100. A novel Arabic OCR post-processing using rule-based and word context techniques10.1007/s10032-018-0297-y ↗