HYBRID DEEP LEARNING-CROW SEARCH ALGORITHM FOR ACCURATE ARABIC HANDWRITTEN DIGIT RECOGNITION

Abtisam Abdulelah Salim  Azeez

doi:10.30572/2018/KJE/170334

Authors

Abtisam Abdulelah Salim Azeez Ministry of Education, Iraq

DOI:

https://doi.org/10.30572/2018/KJE/170334

Keywords:

Arabic handwritten digit recognition, Convolutional neural network, Crow search algorithm, Hyperparameter optimization, Deep learning, Image preprocessing

Abstract

This paper proposes a hybrid deep learning framework for Arabic handwritten digit recognition by optimizing Convolutional Neural Network (CNN) hyperparameters using the Crow Search Algorithm (CSA). Due to the high variability and structural complexity of Arabic handwritten digits, achieving optimal CNN performance requires efficient and automatic hyperparameter tuning. In the proposed approach, CSA is employed to optimize key CNN hyperparameters, including filter size, number of filters, mini-batch size, and learning rate, with the objective of minimizing classification error. The MADBase dataset is used for evaluation, and preprocessing steps such as normalization, image reshaping, one-hot encoding, noise reduction, and data shuffling are applied to enhance training efficiency and model robustness. The CNN architecture is trained using the optimized hyperparameters obtained through CSA iterations. Experimental results show that the proposed CSA-optimized CNN achieves 99% accuracy on the testing set, demonstrating strong generalization capability and stability. The findings confirm that CSA effectively improves CNN performance while eliminating the need for manual hyperparameter tuning, making the framework suitable for other image classification tasks.

Downloads

Download data is not yet available.

References

Ahlawat, S., Choudhary, A., Nayyar, A., Singh, S. and Yoon, B. (2020) 'Improved handwritten digit recognition using convolutional neural networks (CNN)', Sensors, 20(12), p. 3344 https://doi.org/10.3390/s20123344.

Ahmed, S.S., Mehmood, Z., Awan, I.A. and Yousaf, R.M. (2023) 'A novel technique for handwritten digit recognition using deep learning', Journal of Sensors, 2023(1), p. 2753941 https://doi.org/10.1155/2023/2753941.

Al Akabi, H. and Al-assadi, T. (2025) 'Classification of fault signals based on DCT and deep learning', Kufa Journal of Engineering, 16(4) https://doi.org/10.30572/2018/KJE/160413.

Alkhateeb, J.H. (2020) 'Handwritten Arabic digit recognition using convolutional neural network', International Journal of Communication Networks and Information Security, 12(3), pp. 411-416.

Alsurori, M.H., Mohsen, A.A., Al-Badani, G., Al-Nahari, M., Faisal, T. and Alkasem, S. (2023) 'Review on Arabic handwritten recognition using deep learning and machine learning', in (2023) 3rd International Conference on Emerging Smart Technologies and Applications (eSmarTA), IEEE, pp. 1-8. 10.1109/eSmarTA59349.2023.10293409.

Chychkarov, Y., Serhiienko, A., Syrmamiikh, I. and Kargin, A. (2021) 'Handwritten digits recognition using SVM, KNN, RF and deep learning neural networks', CMIS, 2864, pp. 496-509. 10.32782/cmis/2864 44.

Essam, F., Samy, H. and Wagdy, J. (2023) 'Mlhandwrittenrecognition: Handwritten digit recognition using machine learning algorithms', Journal of Computing and Communication, 2(1), pp. 9-19. 10.21608/jocc.2023.282076.

Fateh, A., Birgani, R.T., Fateh, M. and Abolghasemi, V. (2024) 'Advancing multilingual handwritten numeral recognition with attention-driven transfer learning', IEEE Access, 12, pp. 41381-41395. 10.1109/ACCESS.2024.3378598.

Ghanim, M.F., Mohammed, A. and Sali, A. (2023) 'Arabic/English handwritten digits recognition using MLPs, CNN, RF, and CNN-RF', Al-Rafidain Engineering Journal (AREJ), 28(2), pp. 252-260. https://doi.org/10.33899/rengj.2023.138592.1236.

Hussien, A.G., Amin, M., Wang, M., Liang, G., Alsanad, A., Gumaei, A. and Chen, H. (2020) 'Crow search algorithm: theory, recent advances, and applications', IEEE Access, 8, pp. 173548-173565. 10.1109/ACCESS.2020.3024108.

Joy, P. and Jebadurai, I.J. (2025) 'Detection of hair fall and scalp disorders through ML and image processing', Kufa Journal of Engineering, 16(4) https://doi.org/10.30572/2018/KJE/160406.

Ketkar, N. and Moolayil, J. (2021) 'Convolutional neural networks', in Deep learning with Python: learn best practices of deep learning models with PyTorch, Berkeley, CA: Apress, pp. 197-242. 10.1007/978 1 4842 5364 9_6.

Khudeyer, R.S. and Almoosawi, N.M. (2023) 'Combination of machine learning algorithms and ResNet50 for Arabic handwritten classification', Informatica, 46(9) https://doi.org/10.31449/inf.v46i9.4375.

Kusetogullari, H., Yavariabdi, A., Hall, J. and Lavesson, N. (2021) 'DigitNet: a deep handwritten digit detection and recognition method using a new historical handwritten digit dataset', Big Data Research, 23, p. 100182. https://doi.org/10.1016/j.bdr.2020.100182.

Li, Z., Liu, F., Yang, W., Peng, S. and Zhou, J. (2021) 'A survey of convolutional neural networks: analysis, applications, and prospects', IEEE Transactions on Neural Networks and Learning Systems, 33(12), pp. 6999-7019. 10.1109/TNNLS.2021.3084827.

Meraihi, Y., Gabis, A.B., Ramdane-Cherif, A. and Acheli, D. (2021) 'A comprehensive survey of Crow Search Algorithm and its applications', Artificial Intelligence Review, 54(4), pp. 2669-2716. 10.1007/s10462-020-09911-9.

Mezghani, A., Maalej, R., Elleuch, M. and Kherallah, M. (2023) 'Recent advances of ML and DL approaches for Arabic handwriting recognition: a review', International Journal of Hybrid Intelligent Systems, 19(1-2), pp. 61-78. https://doi.org/10.3233/HIS-230005.

Mohamed, N., Josphineleela, R., Madkar, S.R., Sena, J.V., Alfurhood, B.S. and Pant, B. (2023) 'The smart handwritten digits recognition using machine learning algorithm', in (2023) 3rd International Conference on Advance Computing and Innovative Technologies in Engineering (ICACITE), IEEE, pp. 340-344.

Mohammed, H.A., Kareem, S.W. and Mohammed, A.S. (2022) 'A comparative evaluation of deep learning methods in digital image classification', Kufa Journal of Engineering, 13(4) https://doi.org/10.30572/2018/KJE/130405.

Mutawa, A.M., Allaho, M.Y. and Al-Hajeri, M. (2024) 'Machine learning approach for Arabic handwritten recognition', Applied Sciences, 14(19), p. 9020. https://doi.org/10.3390/app14199020.

Prasad, M.L., Srinivasulu, C., Yashaswini, G. and Rakshitha, K. (2023) 'Decoding digits: advancements in handwritten digit recognition with machine learning algorithms', in (2023) International Conference on Recent Advances in Science and Engineering Technology (ICRASET), IEEE, pp. 1-6. 10.1109/ICRASET59632.2023.10420054.