Investigating Shallow Learning Methods for Optical Character Recognition of Indonesia’s Nusantara Scripts
DOI:
https://doi.org/10.29207/resti.v9i6.6648Keywords:
balinese, javanese, optical character recognition, shallow learning, sundaneseAbstract
Indonesia has numerous regional scripts—or so-called Nusantara scripts—and recognizing them is important to preserve Indonesia's cultural heritage. The advances of AI and computer vision technologies make it possible for a machine to optically read the handwritten scripts through the Optical Character Recognition (OCR) technique. However, collecting some of the top OCR solutions and comprehensively investigating their performances on the Nusantara scripts is currently lacking. This study investigates and evaluates some shallow learning-based methods on our newly introduced datasets, consisting of more than 38,000-character images across 80 letter classes in total; here, we focus on three regional scripts: Javanese, Sundanese, and Balinese. The methods include Random Forest, SVM, Logistic Regression, and Gaussian Naïve Bayes, as well as boosting techniques such as XGBoost, Light GBM, and CatBoost. A 5-fold cross-validation approach assessed model performance based on accuracy, precision, recall, and F1-score. Based on the experimental results, the methods demonstrated their competitiveness in reaching the best models for scripts; in particular, XGBoost, Light GBM, and Random Forest-Gini were the winners for Javanese, Sundanese, and Balinese scripts, respectively. These findings demonstrate the effectiveness of ensemble learning methods for diverse handwritten scripts. Comparative analysis to prior deep learning studies is also discussed in this paper. In addition, this research also contributes to preserving Indonesian traditional scripts, as well as offers insights for future regional OCR in other countries.
Downloads
References
I. Krismayani, J. Jumino, and J. Wasisto, “Selected Webliographies on Indonesian Cultural Heritages,” in E3S Web of Conferences, EDP Sciences, 2021, p. 05008. Accessed: Dec. 14, 2024. [Online]. Available: https://www.e3s-conferences.org/articles/e3sconf/abs/2021/93/e3sconf_icenis2021_05008/e3sconf_icenis2021_05008.html
A. Zainal, M. Raden, R. Rustopo, and T. Haryono, “Transforming Sundanese Script From Palm Leaf to Digital Typography,” vol. 509, no. Icollite, pp. 645–652, 2020.
E. S. N. Sumarlina, R. S. M. Permana, and U. A. Darsa, “The Role of Sundanese Letters as the One of Identity and Language Preserver,” 2020, Accessed: Dec. 14, 2024. [Online]. Available: https://books.google.com/books?hl=en&lr=&id=xB0oEAAAQBAJ&oi=fnd&pg=PA273&dq=The+Role+of+Sundanese+Letters+as+the+One+of+Identity+and+Language+Preserver&ots=QP5FnH8lO5&sig=nviMD_rTkH-T9L72DScnIGE2_Xs
Y. A. Ajani, B. D. Oladokun, S. A. Olarongbe, M. N. Amaechi, N. Rabiu, and M. T. Bashorun, “Revitalizing Indigenous Knowledge Systems via Digital Media Technologies for Sustainability of Indigenous Languages,” Preservation, Digital Technology & Culture, vol. 53, no. 1, pp. 35–44, Apr. 2024, doi: 10.1515/pdtc-2023-0051.
I. U. W. M. Susanto, C. A. Sari, E. H. Rachmawanto, and D. R. I. M. Setiadi, “Javanese Script Recognition based on Metric, Eccentricity and Local Binary Pattern,” 2021 International Seminar on Application for Technology of Information and Communication (iSemantic), Sep. 2021, doi: 10.1109/isemantic52711.2021.9573232.
C. A. S. Susanto, E. H. Rachmawanto, I. U. W. Mulyono, and N. M. Yaacob, “A Comparative Study of Javanese Script Classification with GoogleNet, DenseNet, ResNet, VGG16 and VGG19,” Scientific Journal of Informatics, vol. 11, no. 1, pp. 31–40, Jan. 2024, doi: 10.15294/sji.v11i1.47305.
R. Widiarti and F. T. Adji, “Enhancing the Transliteration of Words written in Javanese Script through Augmented Reality,” etasr.com, Oct. 2024, doi: 10.48084/etasr.8312.
M. A. Rasyidi, T. Bariyah, Y. I. Riskajaya, and A. D. Septyani, “Classification of handwritten Javanese script using random forest algorithm,” Bulletin of Electrical Engineering and Informatics, vol. 10, no. 3, pp. 1308–1315, May 2021, doi: 10.11591/eei.v10i3.3036.
A. Pratama, M. D. Sulistiyo, and A. F. Ihsan, “Balinese Script Handwriting Recognition Using Faster R-CNN,” Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), vol. 7, no. 6, pp. 1268–1275, Nov. 2023, doi: 10.29207/resti.v7i6.5176.
M. H. Faishal, M. D. Sulistiyo, and A. F. Ihsan, “Javanese Script Letter Detection Using Faster R-CNN,” Indonesian Journal of Artificial Intelligence and Data Mining, vol. 6, no. 2, p. 243, Aug. 2023, doi: 10.24014/ijaidm.v6i2.24641.
Ö. F. Ertuğrul, J. M. Guerrero, and M. Yilmaz, “Shallow Learning vs. Deep Learning: A Practical Guide for Machine Learning Solutions,” Springer, 2024.
Y. Meir, O. Tevet, Y. Tzach, S. Hodassman, R. D. Gross, and I. Kanter, “Efficient shallow learning as an alternative to deep learning,” Sci. Rep., vol. 13, no. 1, pp. 1–7, 2023, doi: 10.1038/s41598-023-32559-8.
V.-H. Nhu and others, “Comparison of Support Vector Machine, Bayesian Logistic Regression, and Alternating Decision Tree Algorithms for Shallow Landslide Susceptibility Mapping along a Mountainous Road in the West of Iran,” Applied Sciences, vol. 10, no. 15, p. 5047, Jul. 2020, doi: 10.3390/app10155047.
G. Tzougas and K. Kutzkov, “Enhancing Logistic Regression Using Neural Networks for Classification in Actuarial Learning,” Algorithms, vol. 16, no. 2, p. 99, Feb. 2023, doi: 10.3390/a16020099.
Goel and D. Gorse, “Deep vs. Shallow Learning: A Benchmark Study in Low Magnitude Earthquake Detection.” [Online]. Available: https://arxiv.org/abs/2205.00525
P. Schober and T. R. Vetter, “Logistic Regression in Medical Research,” Anesth. Analg., vol. 132, no. 2, pp. 365–366, 2021, doi: 10.1213/ANE.0000000000005247.
J. J. Levy and A. J. O’Malley, “Don’t dismiss logistic regression: the case for sensible extraction of interactions in the era of machine learning,” BMC Medical Research Methodology, vol. 20, no. 1, Jun. 2020, doi: 10.1186/s12874-020-01046-3.
V.-H. Dang and N.-D. Hoang, “L.-M.-D,” Nguyen, D. T. Bui, and P. Samui, “A Novel GIS-Based Random Forest Machine Algorithm for the Spatial Prediction of Shallow Landslide Susceptibility, “Forests, vol. 11, no. 1, p. 118, Jan. 2020, doi: 10.3390/f11010118.
M. Ismail, N. Hassan, and S. S. Bafjaish, “Comparative Analysis of Naive Bayesian Techniques in Health-Related for Classification Task,” J. Soft Comput. Data Min., vol. 1, no. 2, pp. 1–10, 2020, doi: 10.30880/jscdm.2020.01.02.001.
Wickramasinghe and H. Kalutarage, “Naive Bayes: applications, variations and vulnerabilities: a review of literature with code snippets for implementation,” Soft Computing, vol. 25, no. 3, pp. 2277–2293, Sep. 2020, doi: 10.1007/s00500-020-05297-6.
R. Iranzad and X. Liu, “A review of random forest-based feature selection methods for data science education and applications,” International Journal of Data Science and Analytics, Feb. 2024, doi: 10.1007/s41060-024-00509-w.
H. A. Salman, A. Kalakech, and A. Steiti, “Random Forest Algorithm Overview,” Babylonian J. Mach. Learn., vol. 2024, pp. 69–79, 2024, doi: 10.58496/bjml/2024/007.
M. S. Hosen and R. Amin, “Significant of Gradient Boosting Algorithm in Data Management System,” Eng. Int., vol. 9, no. 2, pp. 85–100, 2021, doi: 10.18034/ei.v9i2.559.
F. G. Boldini, D. Kuhn, L. Friedrich, and S. A. Sieber, “Practical guidelines for the use of gradient boosting for molecular property prediction,” Journal of Cheminformatics, vol. 15, no. 1, Aug. 2023, doi: 10.1186/s13321-023-00743-7.
Mljourney, “XGBoost vs LightGBM: Detailed Comparison - ML Journey.” [Online]. Available: https://mljourney.com/xgboost-vs-lightgbm-detailed-comparison/
“XGBoost, “vs LightGBM: Gradient Boosting in the Spotlight.” [Online]. Available: https://dataheadhunters.com/academy/xgboost-vs-lightgbm-gradient-boosting-in-the-spotlight/
Mlq, “Ai, ‘XGBoost and LightGBM | Machine Learning Course.’” [Online]. Available: https://mlq.ai/academy/machine-learning/5/xgboost-lightgbm/
A. C. Bentéjac and G. Martínez-Muñoz, “A comparative analysis of gradient boosting algorithms,” Artificial Intelligence Review, vol. 54, no. 3, pp. 1937–1967, Aug. 2020, doi: 10.1007/s10462-020-09896-5.
A. Susanto, I. U. W. Mulyono, C. A. Sari, E. H. Rachmawanto, M. De Rosal Ignatius Moses Setiadi, and K. Sarker, “Handwritten Javanese script recognition method based 12-layers deep convolutional neural network and data augmentation,” Int J Artif Intell ISSN, vol. 2252, no. 8938, p. 1449, 2023.
E. Paulus, M. Suryani, S. Hadi, and F. Natsir, “An initial study to solve imbalance sundanese handwritten dataset in character recognition,” in 2018 Third International Conference on Informatics and Computing (ICIC), IEEE, 2018, pp. 1–6. Accessed: Dec. 15, 2024. [Online]. Available: https://ieeexplore.ieee.org/abstract/document/8780496/
Text Image Recognition Using Convolutional Neural Networks,” in 2022 International Electronics Symposium (IES), IEEE, 2022, pp. 534–539. Accessed: Dec. 15, 2024. [Online]. Available: https://ieeexplore.ieee.org/abstract/document/9888527/
M. R. Rifaldy, “Implementation Of Architecture LeNet-5 For Javanese Scripts Handwriting Recognition,” in FoITIC: The 3rd Faculty of Industrial Technology International Congress, 2021. Accessed: Dec. 15, 2024. [Online]. Available: https://econference.itenas.ac.id/index.php/foitic2021/foitic2021/paper/view/17
I. G. N. A. C. Putra et al., “Implementasi Metode Convolutional Neural Network Pada Pengenalan Aksara Bali Berbasis Game Edukasi,” SINTECH (Science and Information Technology) Journal, vol. 6, no. 1, pp. 1–15, 2023.
G. Indrawan, A. Asroni, L. J. E. Dewi, I. G. A. Gunadi, and I. K. Paramarta, “Balinese Script Recognition Using Tesseract Mobile Framework,” Lontar Komputer: Jurnal Ilmiah Teknologi Informasi, vol. 13, no. 3, p. 160, 2022.
I. Maliki and A. Febriansyah, “Implementation of Convolutional Neural Network–Extreme Learning Machine for Handwriting Recognition of Sundanese Script,” in 2023 9th International Conference on Signal Processing and Intelligent Systems (ICSPIS), IEEE, 2023, pp. 1–4. Accessed: Dec. 15, 2024. [Online]. Available: https://ieeexplore.ieee.org/abstract/document/10402761/
Y. A. Gerhana, A. R. Atmadja, and M. F. Padilah, “Comparison of Template Matching Algorithm and Feature Extraction Algorithm in Sundanese Script Transliteration Application using Optical Character Recognition,” Jurnal Online Informatika, vol. 5, no. 1, pp. 73–80, 2020.
Downloads
Published
Issue
Section
License
Copyright in each article belongs to the author
- The author acknowledges that the RESTI Journal (System Engineering and Information Technology) is the first publisher to publish with a license Creative Commons Attribution 4.0 International License.
- Authors can enter writing separately, arrange the non-exclusive distribution of manuscripts that have been published in this journal into other versions (eg sent to the author's institutional repository, publication in a book, etc.), by acknowledging that the manuscript has been published for the first time in the RESTI (Rekayasa Sistem dan Teknologi Informasi) journal ;
