Arabic Character Recognition Using CNN LeNet-5

Gibran Satya Nugraha - Mataram University, Mataram, 83125, Indonesia
I Gede Pasek Suta Wijaya - Mataram University, Mataram, 83125, Indonesia
Fitri Bimantoro - Mataram University, Mataram, 83125, Indonesia
Ario Yudo Husodo - Mataram University, Mataram, 83125, Indonesia
Faqih Hamami - Telkom University, Bandung, 40257, Indonesia

Citation Format:



The human handwriting pattern is one of the research areas of pattern recognition; it is very complex. Therefore, research in this field has become quite popular. Moreover, human handwriting pattern recognition is needed for several things, one of them being character recognition. Recognition of Arabic handwriting is complex because everyone has different characteristics in writing and Arabic characters have quite abstract shapes and patterns. From previous research, Convolutional Neural Network (CNN), a deep learning-based algorithm, has a fairly high accuracy value when used for public datasets such as AHDB and private datasets. In this study, private datasets are used with a fairly high level of complexity because the respondents appointed to write Arabic letters come from different age categories. The CNN architecture used in this research is the architecture developed by Yan LeCun known as LeNet-5. The local dataset used was 8400 images, with details of 6720 for training data (each letter has 240 images) and 1680 for testing data (each letter has 60 images). The total respondents who wrote Arabic script were 30 people, and each person wrote each letter ten times. The accuracy obtained is 81% higher than in previous studies. The following study will test a number of additional CNN architectures to increase the accuracy of the results. In addition to accuracy, this study will also calculate the misclassification rate, root mean square error, and mean absolute error.


Arabic; handwriting; pattern; deep learning; convolutional neural network

Full Text:



M. Yu. Mikheev, Yu. S. Gusynina, and T. A. Shornikova, “Building Neural Network for Pattern Recognition,” 2020 International Russian Automation Conference (RusAutoCon), Sep. 2020, doi:10.1109/rusautocon49822.2020.9208207.

X. Bai et al., “Explainable deep learning for efficient and robust pattern recognition: A survey of recent developments,” Pattern Recognit, vol. 120, p. 108102, 2021.

M. Rajalakshmi, P. Saranya, and P. Shanmugavadivu, “Pattern Recognition-Recognition of Handwritten Document Using Convolutional Neural Networks,” 2019 IEEE International Conference on Intelligent Techniques in Control, Optimization and Signal Processing (INCOS), Apr. 2019, doi:10.1109/incos45849.2019.8951342.

S. I. Ali, S. S. Ebrahimi, M. Khurram, and S. I. Qadri, “Real-Time Face Mask Detection in Deep Learning using Convolution Neural Network,” 2021 10th IEEE International Conference on Communication Systems and Network Technologies (CSNT), Jun. 2021, doi: 10.1109/csnt51715.2021.9509704.

A. Varshney, A. Katiyar, A. K. Singh, and S. S. Chauhan, “Dog Breed Classification Using Deep Learning,” 2021 International Conference on Intelligent Technologies (CONIT), Jun. 2021, doi:10.1109/conit51480.2021.9498338.

K. Neeraja, K. Srinivas Rao, and G. Praneeth, “Deep Learning based Lip Movement Technique for Mute,” 2021 6th International Conference on Communication and Electronics Systems (ICCES), Jul. 2021, doi: 10.1109/icces51350.2021.9489122.

J. Han, G. Kim, C. Lee, Y. Han, U. Hwang, and S. Kim, “Predictive Models of Fire via Deep learning Exploiting Colorific Variation,” 2019 International Conference on Artificial Intelligence in Information and Communication (ICAIIC), Feb. 2019, doi:10.1109/icaiic.2019.8669042.

T. Singh, S. R. Kudavelly, and K. Venkata Suryanarayana, “Deep Learning Based Fetal Face Detection And Visualization In Prenatal Ultrasound,” 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI), Apr. 2021, doi: 10.1109/isbi48211.2021.9433915.

F. Syuhada, R. Indraswari, A. Z. Arifin, and D. A. Navastara, “Multi-Projection Segmentation on Dental Cone Beam Computed Tomography Images Using Level Set Method,” Journal of Computer Science and Informatics Engineering (J-Cosine), vol. 5, no. 2, pp. 130–139, 2021.

A. K. Agrawal, A. K. Shrivas, and V. kumar Awasthi, “A Robust Model for Handwritten Digit Recognition using Machine and Deep Learning Technique,” 2021 2nd International Conference for Emerging Technology (INCET), May 2021, doi:10.1109/incet51464.2021.9456118.

N. Darapaneni et al., “Handwritten Form Recognition Using Artificial Neural Network,” 2020 IEEE 15th International Conference on Industrial and Information Systems (ICIIS), Nov. 2020, doi:10.1109/iciis51140.2020.9342638.

P. Raundale and H. Maredia, “Analytical Study of Handwritten Character Recognition: A Deep Learning Way,” 2021 International Conference on Intelligent Technologies (CONIT), Jun. 2021, doi:10.1109/conit51480.2021.9498347.

S.-Y. Wang, O. Wang, R. Zhang, A. Owens, and A. A. Efros, “CNN-Generated Images Are Surprisingly Easy to Spot… for Now,” 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 2020, doi: 10.1109/cvpr42600.2020.00872.

I. Ahmed, M. Ahmad, F. A. Khan, and M. Asif, “Comparison of Deep-Learning-Based Segmentation Models: Using Top View Person Images,” IEEE Access, vol. 8, pp. 136361–136373, 2020, doi:10.1109/access.2020.3011406.

S. Dong, P. Wang, and K. Abbas, “A survey on deep learning and its applications,” Comput Sci Rev, vol. 40, p. 100379, 2021.

D. Kollias and S. Zafeiriou, “Exploiting Multi-CNN Features in CNN-RNN Based Dimensional Emotion Recognition on the OMG in-the-Wild Dataset,” IEEE Transactions on Affective Computing, vol. 12, no. 3, pp. 595–606, Jul. 2021, doi: 10.1109/taffc.2020.3014171.

M. Sreenivasulu and M. Sridevi, “Comparative study of statistical features to detect the target event during disaster,” Big Data Mining and Analytics, vol. 3, no. 2, pp. 121–130, Jun. 2020, doi:10.26599/bdma.2019.9020021.

M. Eltay, A. Zidouri, and I. Ahmad, “Exploring Deep Learning Approaches to Recognize Handwritten Arabic Texts,” IEEE Access, vol. 8, pp. 89882–89898, 2020, doi: 10.1109/access.2020.2994248.

Y. Hamdi, H. Boubaker, and A. M. Alimi, “Online Arabic handwriting recognition using graphemes segmentation and deep learning recurrent neural networks,” in Enabling Machine Learning Applications in Data Science, Springer, 2021, pp. 281–297.

N. Alrobah and S. Albahli, “A Hybrid Deep Model for Recognizing Arabic Handwritten Characters,” IEEE Access, vol. 9, pp. 87058–87069, 2021, doi: 10.1109/access.2021.3087647.

A. Alsaeedi, H. A. Mutawa, S. Snoussi, S. Natheer, K. Omri, and W. A. Subhi, “Arabic words Recognition using CNN and TNN on a Smartphone,” 2018 IEEE 2nd International Workshop on Arabic and Derived Script Analysis and Recognition (ASAR), Mar. 2018, doi:10.1109/asar.2018.8480267.

H. M. Al-Barhamtoshy, K. M. Jambi, S. M. Abdou, and M. A. Rashwan, “Arabic Documents Information Retrieval for Printed, Handwritten, and Calligraphy Image,” IEEE Access, vol. 9, pp. 51242–51257, 2021, doi: 10.1109/access.2021.3066477.

O. A. Almansari and N. N. W. N. Hashim, “Recognition of Isolated Handwritten Arabic Characters,” 2019 7th International Conference on Mechatronics Engineering (ICOM), Oct. 2019, doi:10.1109/icom47790.2019.8952035.

Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, no. 7553, pp. 436–444, May 2015, doi: 10.1038/nature14539.

N. Kasim and G. S. Nugraha, “Pengenalan Pola Tulisan Tangan Aksara Arab Menggunakan Metode Convolution Neural Network,” Jurnal Teknologi Informasi, Komputer, dan Aplikasinya (JTIKA), vol. 3, no. 1, pp. 85–95, 2021.

M. Kayed, A. Anter, and H. Mohamed, “Classification of Garments from Fashion MNIST Dataset Using CNN LeNet-5 Architecture,” 2020 International Conference on Innovative Trends in Communication and Computer Engineering (ITCE), Feb. 2020, doi: 10.1109/itce48509.2020.9047776.

J. D. Bodapati, U. Srilakshmi, and N. Veeranjaneyulu, “FERNet: A Deep CNN Architecture for Facial Expression Recognition in the Wild,” Journal of The Institution of Engineers (India): Series B, pp. 1–10, 2021.

Z. A. Sejuti and M. S. Islam, “An efficient method to classify brain tumor using CNN and SVM,” in 2021 2nd International Conference on Robotics, Electrical and Signal Processing Techniques (ICREST), 2021, pp. 644–648.

M. Bhuvaneshwari and E. G. M. Kanaga, “Convolutional Neural Network for Addiction Detection using Improved Activation Function,” in 2021 5th International Conference on Computing Methodologies and Communication (ICCMC), 2021, pp. 996–1000.

K. Chakraborty, S. Bhattacharyya, R. Bag, and A. A. Hassanien, “Sentiment Analysis on a Set of Movie Reviews Using Deep Learning Techniques,” Social Network Analytics, pp. 127–147, 2019, doi:10.1016/b978-0-12-815458-8.00007-4.

A. El-Sawy, H. EL-Bakry, and M. Loey, “CNN for Handwritten Arabic Digits Recognition Based on LeNet-5,” Proceedings of the International Conference on Advanced Intelligent Systems and Informatics 2016, pp. 566–575, Oct. 2016, doi: 10.1007/978-3-319-48308-5_54.