Hangul Handwritten One-Syllable Character Recognition Using CNN With ResNet Architecture and SVM

Rena Rama Rosalinda; Basuki  Rahmat; Eka Prakarsa Mandyartha

doi:10.59934/jaiea.v5i1.1702

Authors

Rena Rama Rosalinda Universitas Pembangunan Nasional “Veteran” Jawa Timur
Basuki Rahmat Universitas Pembangunan Nasional “Veteran” Jawa Timur
Eka Prakarsa Mandyartha Universitas Pembangunan Nasional “Veteran” Jawa Timur

DOI:

https://doi.org/10.59934/jaiea.v5i1.1702

Keywords:

Convolutional Neural Network (CNN), Handwritten Recognition, Residual Network (ResNet), Support Vector Machine (SVM)

Abstract

Foreign language skills are one of the gateways to opening up opportunities for better education and employment. The use of technology can help with this, especially handwriting recognition technology. However, the use of limited datasets is often a problem. This study uses a Convolutional Neural Network (CNN) model with a Residual Network (ResNet) architecture and a Support Vector Machine (SVM). ResNet, as a feature extraction method for the data, is capable of capturing data patterns without losing much of the original data information. Meanwhile, the SVM algorithm, as a data classifier, is capable of working well with limited data. This research uses hyperparameters of linear kernel, polynomial kernel, Radial Basis Function (RBF) kernel, and Sigmoid kernel. Additionally, the hyperparameters C and Gamma values were also used. The research results indicate that the best model accuracy was obtained from the model trained with a linear kernel and a C value of 0.1, with an accuracy of 81.72% and an accuracy on the test data of 87.50%.

Downloads

Download data is not yet available.

References

R. Budiawan, I. Arief, R. Munir, and D. Mahayana, “Pergeseran Paradigma pada Penelitian Pengenalan Tulisan Tangan,” Jurnal Filsafat Indonesia Undiksha, Jun. 2023.

L. Windrim, R. Ramakrishnan, A. Melkumyan, and R. J. Murphy, “Hyperspectral CNN Classification with Limited Training Samples.”

L. M. Abu Zohair, “Prediction of Student’s performance by modelling small dataset size,” International Journal of Educational Technology in Higher Education, vol. 16, no. 1, Dec. 2019, doi: 10.1186/s41239-019-0160-3.

C.-S. Yang and C.-C. Hsieh, “High Accuracy Text Detection using ResNet as Feature Extractor,” in 2019 IEEE Eurasia Conference on IOT, Communication and Engineering (ECICE), 2019, pp. 92–95. doi: 10.1109/ECICE47484.2019.8942666.

S. Rahayu, S. Sandiwarno, E. D. Putra, M. Utami, and H. Setiawan, “Model Sequential Resnet50 Untuk Pengenalan Tulisan Tangan Aksara Arab Article Info ABSTRAK,” JSAI: Journal Scientific and Applied Informatics, vol. 06, no. 02, 2023, doi: 10.36085.

F. Muhammad, A. Murni Arimurthy, and D. Chahyati, “Transfer Learning dengan Metode Fine Tuning pada Model Network VGG16 dan ResNet50,” Indonesian Journal of Computer Science Attribution (2023), vol. 12, no. 1, p. 361, 2023.

F. Islam, M. H. Rahman, Nurjahan, M. S. Hossain, and S. Ahmed, “A Novel Method for Diagnosing Alzheimer’s Disease from MRI Scans using the ResNet50 Feature Extractor and the SVM Classifier,” International Journal of Advanced Computer Science and Applications, vol. 14, no. 6, pp. 1233–1242, 2023, doi: 10.14569/IJACSA.2023.01406131.

A. Y. Mahmoud, “Preliminary Introduction and Implementation of Novel Machine Learning Algorithm Utilising Pareto Principle: Classification of Small Biomedical Health-Related Datasets,” in Advances in Computational Intelligence Systems, M. and M. L. S. Panoutsos George and Mahfouf, Ed., Cham: Springer Nature Switzerland, 2024, pp. 129–141.

H. Tabrizchi, M. M. Javidi, and V. Amirzadeh, “Estimates of residential building energy consumption using a multi-verse optimizer-based support vector machine with k-fold cross-validation,” Evolving Systems, vol. 12, no. 3, pp. 755–767, Sep. 2021, doi: 10.1007/s12530-019-09283-8.