Predicting Dyslexia in Arabic-Speaking Children Through Handwritten Images Using Deep Learning Methods
DOI:
https://doi.org/10.26713/cma.v15i5.3309Keywords:
Dyslexia, Deep Learning, Dyslexia Prediction, Dyslexia Classification, Handwritten Image, Handwriting Recognition, CNNAbstract
Dyslexia is categorized as an educational disorder that affects the ability to spell, read, and write. It is considered one of the most common learning difficulties in Saudi Arabian schools. Research has demonstrated the close connection between the reading and writing processes; moreover, deficiencies or difficulties in an individual’s reading process have been associated with difficulties in writing. In this paper, we utilized a novel method to reveal dyslexia among children in elementary school in Saudi Arabia using handwritten images of alphabet letters. We present new datasets of Arabic letters written by children aged 7-10 in early childhood schools in Jeddah, Saudi Arabia. These datasets contain 3,611 characters written by two groups of children: one comprised of children who suffered from dyslexia and one without this disorder. Furthermore, we propose a Convolutional Neural Network (CNN) model for the automatic detection of dyslexia using handwriting. The results demonstrate that our model exhibits outstanding performance, attaining accuracy levels of 95.30% and 95.97% before and after the data augmentation technique, respectively, on our dataset.
Downloads
References
S. Abu-rabia and H. Taha, Reading and spelling error analysis of native, Reading and Writing 17(7-8) (2004), 651 – 690, DOI: 10.1007/s11145-004-2657-x.
W. Albattah and S. Albahli, Intelligent Arabic handwriting recognition using different standalone and hybrid CNN architectures, Applied Sciences 12(19) (2022), 10155, DOI: 10.3390/app121910155.
M. N. AlJarrah, M. M. Zyout and R. Duwairi, Arabic handwritten characters recognition using convolutional neural network, in: 2021 12th International Conference on Information and Communication Systems (ICICS2021, Valencia, Spain, 2021), pp. 182 – 188 (2021), DOI: 10.1109/ICICS52457.2021.9464596.
N. D. Alqahtani, B. Alzahrani and M. S. Ramzan, Deep learning applications for dyslexia prediction, Applied Sciences 13(5) (2023), 2804, DOI: 10.3390/app13052804.
N. Alrobah and S. Albahli, A hybrid deep model for recognizing Arabic handwritten characters, IEEE Access 9 (2021), 87058 – 87069, DOI: 10.1109/ACCESS.2021.3087647.
N. Altwaijry and I. Al-Turaiki, Arabic handwriting recognition system using convolutional neural network, Neural Computing and Applications 33(7) (2021), 2249 – 2261, DOI: 10.1007/s00521-020-05070-8.
H. M. Balaha, H. A. Ali, E. K. Youssef, A. E. Elsayed, R. A. Samak, M. S. Abdelhaleem, M. M. Tolba, M. R. Shehata, M. R. Mahmoud, M. M. Abdelhameed and M. M. Mohammed, Recognizing arabic handwritten characters using deep learning and genetic algorithms, Multimedia Tools and Applications 80(21-23) (2021), 32473 – 32509, DOI: 10.1007/s11042-021-11185-4.
G. Cohen, S. Afshar, J. Tapson and A. Van Schaik, EMNIST: Extending MNIST to handwritten letters, in: Proceedings of the 2017 International Joint Conference on Neural Networks (IJCNN, Anchorage, AK, USA, 2017), pp. 2921 – 2926, (2017), DOI: 10.1109/IJCNN.2017.7966217.
A. El-Sawy, H. EL-Bakry and M. Loey, CNN for handwritten Arabic digits recognition based on LeNet-5, in: Proceedings of the International Conference on Advanced Intelligent Systems and Informatics (AISI 2016, Advances in Intelligent Systems and Computing), A. Hassanien, K. Shaalan, T. Gaber, A. Azar and M. Tolba (editors), Vol. 533, Springer, Cham., (2017), DOI: 10.1007/978-3-319-48308-5_54.
J.-P. Fischer and C. Luxembourger, Commentary: Mirror-image equivalence and interhemispheric mirror-image reversal, Frontiers in Human Neuroscience 12 (2018), 140, DOI: 10.3389/fnhum.2018.00375.
G. D. Germano, C. Giaconi and S. Capellini, Characterization of Brazilians students with dyslexia in handwriting proficiency screening questionnaire and handwriting scale, Psychology Research 6(10) (2016), 590 – 597, DOI: 10.17265/2159-5542/2016.10.004.
M. Hebert, D. M. Kearns, J. B. Hayes, P. Bazis and S. Cooper, Why children with dyslexia struggle with writing and how to help them, Language, Speech, and Hearing Services in Schools 49(4) (2018), 843 – 863, DOI: 10.1044/2018_LSHSS-DYSLC-18-002.
L. Khreisat, A machine learning approach for Arabic text classification using N-gram frequency statistics, Journal of Informetrics 3(1) (2009), 72 – 77, 2009, DOI: 10.1016/j.joi.2008.11.005.
T. Lachmann, Experimental approaches to specific disabilities in learning to read: The case of Symmetry Generalization in developmental dyslexia, in: Advances in Cognitive Science, N. A. Srinivasan, K. Gupta and J. Pandey, Sage, Thousand Oaks, CA, pp. 321 – 342 (2008).
R. Larasati and H. Keunglam, Handwritten digits recognition using ensemble neural networks and ensemble decision tree, in: Proceedings of the 2017 International Conference on Smart Cities, Automation & Intelligent Computing Systems (ICON-SONICS Yogyakarta, Indonesia, 2017), pp. 99 – 104, (2017), DOI: 10.1109/ICON-SONICS.2017.8267829.
W. Luo, Y. Li, R. Urtasun and R. Zemel, Understanding the effective receptive field in deep convolutional neural networks, in: Proceedings of the 30th Conference on Neural Information Processing Systems (NIPS’16, Barcelona, Spain), Curran Associates Inc., Red Hook, NY, USA, pp. 4905 – 4913, (2016), DOI: 10.5555/3157382.3157645.
V. Madane, K. Ovhal and M. Bhong, Handwriting recognition using artificial intelligence neural network and image processing, International Research Journal of Modernization in Engineering Technology and Science 5(3) (2023), 1432 – 1447, DOI: 10.56726/irjmets34395.
A. F. Nurjannah, A. S. D. Kurniasari, Z. Sari and Y. Azhar, Pneumonia image classification using CNN with max pooling and average pooling, Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) 5(2) (2021), 330 – 338, DOI: 10.29207/resti.v6i2.4001.
V. Pham, T. Bluche, C. Kermorvant and J. Louradour, Dropout improves recurrent neural networks for handwriting recognition, in: Proceedings of the 14th International Conference on Frontiers in Handwriting Recognition (Greece, 2014, pp. 285 – 290), (2014), DOI: 10.1109/ICFHR.2014.55.
K. Shaalan, S. Siddiqui, M. Alkhatib and A. A. Monem, Chapter 3: Challenges in Arabic natural language processing, in: Computational Linguistics, Speech and Image Processing for Arabic Language, pp. 59 – 83 2018, DOI: 10.1142/9789813229396_0003.
S. Shaywitz, Overcoming dyslexia: A new and complete science-based program for reading problems at any level, 1st edition, Alfred A. Knopf, Inc., New York, USA, ix + 414 pages (2003).
C. Song, W. Xu, Z. Wang, S. Yu, P. Zeng and Z. Ju, Analysis on the impact of data augmentation on target recognition for UAV-based transmission line inspection, Complexity 2020(1) (2020), 3107450, DOI: 10.1155/2020/3107450.
K. Spoon, K. Siek, D. Crandall and M. Fillmore, Can we (and should we) use AI to detect dyslexia in children’s handwriting?, in: Proceedings of the AI for Social Good workshop at NeurIPS (2019), Vancouver, Canada, pp. 1 – 6, (2019).
A. A. Yahya, J. Tan and M. Hu, A novel handwritten digit classification system based on convolutional neural network approach, Sensors 21(18) (2021), 6273, DOI: 10.3390/s21186273.
K. Zhang, W. Zuo, Y. Chen, D. Meng and L. Zhang, Beyond a Gaussian denoiser: Residual learning of deep CNN for image denoising, IEEE Transactions on Image Processing 26(7) (2017), 3142 – 3155, DOI: 10.1109/TIP.2017.2662206.
Downloads
Published
How to Cite
Issue
Section
License
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a CCAL that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
