Advanced approach for Moroccan administrative documents digitization using pre-trained models CNN-based: character recognition

Ali Benaissa, Abdelkhalak Bahri, Ahmad El Allaoui, My Abdelouahab Salahddine

Abstract


In the digital age, efficient digitization of administrative documents is a real challenge, particularly for languages with complex scripts such as those used in Moroccan documents. The subject matter of this article is the digitization of Moroccan administrative documents using pre-trained convolutional neural networks (CNNs) for advanced character recognition. This research aims to address the unique challenges of accurately digitizing various Moroccan scripts and layouts, which are crucial in the digital transformation of administrative processes. Our goal was to develop an efficient and highly accurate character recognition system specifically tailored for Moroccan administrative texts. The tasks involved comprehensive analysis and customization of pre-trained CNN models and rigorous performance testing against a diverse dataset of Moroccan administrative documents. The methodology entailed a detailed evaluation of different CNN architectures trained on a dataset representative of various types of characters used in Moroccan administrative documents. This ensured the adaptability of the models to real-world scenarios, with a focus on accuracy and efficiency in character recognition. The results were remarkable. DenseNet121 achieved a 95.78% accuracy rate on the Alphabet dataset, whereas VGG16 recorded a 99.24% accuracy on the Digits dataset. DenseNet169 demonstrated 94.00% accuracy on the Arabic dataset, 99.9% accuracy on the Tifinagh dataset, and 96.24% accuracy on the French Special Characters dataset. Furthermore, DenseNet169 attained 99.14% accuracy on the Symbols dataset. In addition, ResNet50 achieved 99.90% accuracy on the Character Type dataset, enabling accurate determination of the dataset to which a character belongs. In conclusion, this study signifies a substantial advancement in the field of Moroccan administrative document digitization. The CNN-based approach showcased in this study significantly outperforms traditional character recognition methods. These findings not only contribute to the digital processing and management of documents but also open new avenues for future research in adapting this technology to other languages and document types.

Keywords


Character Recognition; Pre-trained Models; Convolutional Neural Networks (CNNs); Moroccan Official Documents; Digital Transformation

Full Text:

PDF

References


Geron, A. Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems. 2nd edition, O'Reilly Media, Inc., 2019. 856 p. ISBN: 978-1492032649.

Thorat, C., Bhat, A., Sawant, P., Bartakke, I., & Shirsath, S. A Detailed Review on Text Extraction Using Optical Character Recognition. In: FONG, S., DEY, N. & JOSHI, A., eds. ICT Analysis and Applications, Lecture Notes in Networks and Systems, 2022, vol. 314, Singapore: Springer Nature Singapore, pp. 719-728. DOI: 10.1007/978-981-16-5655-2_69.

Radwan, M. A., Khalil, M. I., & Abbas, H. M. Neural Networks Pipeline for Offline Machine Printed Arabic OCR. Neural Processing Letters. 2018, vol. 48, no. 2, pp. 769-787. DOI: 10.1007/s11063-017-9727-y.

Gong, Y., Yang, J., & Shi, X. Towards a comprehensive understanding of digital transformation in government: Analysis of flexibility and enterprise architecture. Government Information Quarterly. 2020, vol. 37, no. 3, article no. 101487. DOI: 10.1016/j.giq.2020.101487.

Kadhim, A. I. Survey on supervised machine learning techniques for automatic text classification. Artificial Intelligence Review. 2019, vol. 52, no. 1, pp. 273-292. DOI: 10.1007/s10462-018-09677-1.

Sen, P. C., Hajra, M., & Ghosh, M. Supervised Classification Algorithms in Machine Learning: A Survey and Review. In: MANDAL, J. K. & BHATTACHARYA, D., eds. Emerging Technology in Modelling and Graphics. Advances in Intelligent Systems and Computing, 2020, vol. 937, Singapore: Springer Singapore, pp. 99-111. DOI: 10.1007/978-981-13-7403-6_11.

Khan, A., Laghari, A., & Awan, S. Machine Learning in Computer Vision: A Review. ICST Transactions on Scalable Information Systems, 2021, iss. 32, aricle no. e4. DOI: 10.4108/eai.21-4-2021.169418.

Chukhray, A., Chernenko, M., Stoliarenko, T., & Leshchenko, O. Diagnostic support of intelligent tutor system for teaching skills to construct control object frequency characteristics. Radioelektronni i komp'uterni sistemi – Radioelectronic and computer systems, 2022, no. 3, pp. 190-199. DOI: 10.32620/reks.2022.3.14.

Oumoulylte, M., Omari Alaoui, A., Farhaoui, Y., El Allaoui, A., & Bahri, A. Convolutional neural network-based skin cancer classification with transfer learning models. Radioelektronni i komp'uterni sistemi – Radioelectronic and computer systems, 2023, no. 4, pp. 75-87. DOI: 10.32620/reks.2023.4.07.

Hosen, M. A., Moz, S. H., Khalid, M. M. H., Kabir, S. S., & Galib, D. S. M. Face recognition-based attendance system with anti-spoofing, system alert, and email automation. Radioelektronni i komp'uterni sistemi – Radioelectronic and computer systems, 2023, no. 2, pp. 119-128. DOI: 10.32620/reks.2023.2.10.

Cob-Parro, A. C., Losada-Gutiérrez, C., Marrón-Romera, M., Gardel-Vicente, A., & Bravo-Muñoz, I. A new framework for deep learning video based Human Action Recognition on the edge. Expert Systems with Applications, 2024, vol. 238, article no. 122220. DOI: 10.1016/j.eswa.2023.122220.

Dovbysh, A., Liubchak, V., Shelehov, I., Simonovskiy, J., & Tenytska, A. Information-extreme machine learning of a cyber attack detection system. Radioelektronni i komp'uterni sistemi – Radioelectronic and computer systems, 2022, no. 3, pp. 121-131. DOI: 10.32620/reks.2022.3.09.

Islam, M. M., Hossain, M. B., Akhtar, M. N., Moni, M. A. & Hasan, K. F. CNN Based on Transfer Learning Models Using Data Augmentation and Transformation for Detection of Concrete Crack. Algorithms, 2022, vol. 15, no. 8, article no. 287. DOI: 10.3390/a15080287.

Liu, Y., Wang, Y., & Shi, H. A Convolutional Recurrent Neural-Network-Based Machine Learning for Scene Text Recognition Application. Symmetry, 2023, vol. 15, no. 4, article no. 849. DOI: 10.3390/sym15040849.

Han, X., Zhang, Z., Ding, N., Gu, Y., Liu, X., Huo, Y., Qiu, J., Yao, Y., Zhang, A., Zhang, L., Han, W., Huang, M., Jin, Q., Lan, Y., Liu, Y., Liu, Z., Lu, Z., Qiu, X., Song, R., Tang, J., Wen, J.-R., Yuan, J., Zhao, W. X., & Zhu, J. Pre-trained models: Past, present and future. AI Open, 2021, vol. 2, pp. 225-250. DOI: 10.1016/j.aiopen.2021.08.002.

Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G. & Isard, M. TensorFlow: A System for Large-Scale Machine Learning. OSDI'16: Proceedings of the 12th USENIX conference on Operating Systems Design and Implementation, November 2016, pp. 265–283.

Hinton, G. E., Osindero, S., & Teh, Y.-W. A fast learning algorithm for deep belief nets. Neural Comput. 2006, vol. 18, no. 7, pp. 1527–1554. DOI: 10.1162/neco.2006.18.7.1527.

Pham, V., Bluche, T., Kermorvant, C., & Louradour, J. Dropout Improves Recurrent Neural Networks for Handwriting Recognition. 14th International Conference on Frontiers in Handwriting Recognition, 2014, pp. 285-290. DOI: 10.1109/ICFHR.2014.55.

Benaissa, A., Bahri, A., & Allaoui, A. E. Characters Type Recognition In Moroccan Documents Using CNN. 2nd International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET), 2022, pp. 1-7. DOI: 10.1109/IRASET52964.2022.9738376.

AlJarrah, M. N., Zyout, M. M., & Duwairi, R. Arabic Handwritten Characters Recognition Using Convolutional Neural Network. 12th International Conference on Information and Communication Systems (ICICS), 2021, pp. 182-188. DOI: 10.1109/ICICS52457.2021.9464596.

Hazra, T. K., Singh, D. P., & Daga, N. Optical character recognition using KNN on custom image dataset. 8th Annual Industrial Automation and Electromechanical Engineering Conference (IEMECON), 2017, pp. 110-114. DOI: 10.1109/IEMECON.2017.8079572.

Prashanth, D. S., Mehta, R. V. K., & Sharma, N. Classification of Handwritten Devanagari Number – An analysis of Pattern Recognition Tool using Neural Network and CNN. Procedia Computer Science. 2020, vol. 167, pp. 2445-2457. DOI: 10.1016/j.procs.2020.03.297.

Albattah, W., & Albahli, S. Intelligent Arabic Handwriting Recognition Using Different Standalone and Hybrid CNN Architectures. Applied Sciences, 2022, vol. 12, iss. 19, article no. 10155. DOI: 10.3390/app121910155.

Luo, C., Li, X., Wang, L., He, J., Li, D., & Zhou, J. How Does the Data set Affect CNN-based Image Classification Performance? 5th International Conference on Systems and Informatics (ICSAI), 2018, pp. 361-366. DOI: 10.1109/ICSAI.2018.8599448.

Benaissa, A., Bahri, A., & El Allaoui, A. Multilingual character recognition dataset for Moroccan official documents. Data in Brief., 2024, vol. 52, article no. 109953. DOI: 10.1016/j.dib.2023.109953.

Kingma, D. P., & Ba, J. Adam: A Method for Stochastic Optimization. CoRR., 2014, vol. abs/1412.6980. DOI: 10.48550/arXiv.1412.6980.

Sashank, Kale, S., & Kumar, S. On the Convergence of Adam and Beyond. arXiv pre-print server, 2019. DOI: 10.48550/arXiv.1904.09237.

Prashanth, D. S., Mehta, R. V. K., Ramana, K., & Bhaskar, V. Handwritten Devanagari Character Recognition Using Modified Lenet and Alexnet Convolution Neural Networks. Wireless Personal Communications, 2022, vol. 122, no. 1, pp. 349-378. DOI: 10.1007/s11277-021-08903-4.

Hamdan, Y. B., & Sathish. Construction of Statistical SVM based Recognition Model for Handwritten Character Recognition. Journal of Information Technology and Digital World, 2021, vol. 3, no. 2, pp. 92-107. DOI: 10.36548/jitdw.2021.2.003.




DOI: https://doi.org/10.32620/reks.2024.1.02

Refbacks

  • There are currently no refbacks.