Balinese Script Handwriting Recognition Using Faster R-CNN
Abstract
In Balinese culture, the ability to read Balinese script is one of the challenges young generations face. Advances in machine learning have proposed handwriting detection systems using both traditional and deep learning models. However, the traditional approach is usually impractical and is prone to inaccurate identification results. Convolutional neural network (CNN)-based models integrate feature extraction and classification into an end-to-end pipeline to increase performance. This research proposes that recognizing characters through an object detection approach makes an end-to-end process of localizing and classifying several characters simultaneously using the Faster R-CNN. Four CNN models, including ResNet-50, ResNet-101, ResNet-152, and Inception ResNet V2, were tested to detect 28 Balinese characters in a single form that covers 18 consonants and 10 digits using Intersection over Union (IoU) thresholds: 0.5 and 0.75. ResNet-50 and Inception ResNet V2 achieve 0.991 mAP at IoU of 0.5, while Inception ResNet V2 excels at IoU of 0.75. Further analysis showed that the class ‘nol’ had the lowest Recall due to many undetected ground truths. Meanwhile, class ‘ba’ had the lowest Precision due to its similarity to classes “ga” and “nga”. This research contributes to the experiment with Faster R-CNN in detecting handwritten Balinese scripts.
Downloads
References
H. M. I. Nahak, “UPAYA MELESTARIKAN BUDAYA INDONESIA DI ERA GLOBALISASI,” Jurnal Sosiologi Nusantara, vol. 5, no. 1, pp. 65–76, Jun. 2019, doi: 10.33369/jsn.5.1.65-76.
M. W. A. Kesiman, G. A. Pradnyana, and I. M. D. Maysanjaya, “Balinese glyph recognition with gabor filters,” in Journal of Physics: Conference Series, Institute of Physics Publishing, Jun. 2020. doi: 10.1088/1742-6596/1516/1/012029.
I. K. A. G. Wiguna and I. M. D. P. Asana, “Implementasi Zoning dan Fitur Arah Sebagai Ekstraksi Fitur Pada Pengenalan Tulisan Tangan Aksara Bali,” Jurnal RESISTOR (Rekayasa Sistem Komputer), vol. 4, no. 1, pp. 85–92, 2021, doi: 10.31598/jurnalresistor.v4i1.751.
M. W. A. Kesiman, “Word recognition for the balinese palm leaf manuscripts,” in Proceedings: CYBERNETICSCOM 2019 - 2019 IEEE International Conference on Cybernetics and Computational Intelligence: Towards a Smart and Human-Centered Cyber World, Institute of Electrical and Electronics Engineers Inc., Aug. 2019, pp. 72–76. doi: 10.1109/CYBERNETICSCOM.2019.8875634.
I. M. Windya, “Dinamika Pasang Aksara Bali: Sebuah Kajian Historis Sistem Ejaan,” Widyacarya: Jurnal Pendidikan, Agama dan Budaya, vol. 2, no. 1, pp. 39–43, 2018, doi: 10.55115/widyacarya.v2i1.62.
B. M. Vinjit, M. K. Bhojak, S. Kumar, and G. Chalak, “A Review on Handwritten Character Recognition Methods and Techniques,” Proceedings of the 2020 IEEE International Conference on Communication and Signal Processing, ICCSP 2020, pp. 1224–1228, 2020, doi: 10.1109/ICCSP48568.2020.9182129.
M. Abuzaraida, M. Elmehrek, and E. Elsomadi, “Online handwriting Arabic recognition system using k-nearest neighbors classifier and DCT features,” International Journal of Electrical and Computer Engineering, vol. 11, pp. 3584–3592, Jun. 2021, doi: 10.11591/ijece.v11i4.pp3584-3592.
G. and A. H. T. and S. D. Hailu Belay Birhanu and Belay, “Multi-font Printed Amharic Character Image Recognition: Deep Learning Techniques,” in Advances of Science and Technology, T. and F. S. W. Zimale Fasikaw Atanaw and Enku Nigussie, Ed., Cham: Springer International Publishing, 2019, pp. 322–331. doi: 10.1007/978-3-030-15357-1_27.
M. Jabde, C. Patil, S. Mali, and A. Vibhute, “Comparative Study of Machine Learning and Deep Learning Classifiers on Handwritten Numeral Recognition,” Jun. 2022. doi: 10.1007/978-981-19-8094-7_10.
A. Adole, E. Edirisinghe, B. Li, and C. Bearchell, “Investigation of Faster-RCNN Inception Resnet V2 on Offline Kanji Handwriting Characters,” ACM International Conference Proceeding Series, 2020, doi: 10.1145/3415048.3416104.
S. Albahli, M. Nawaz, A. Javed, and A. Irtaza, “An improved faster-RCNN model for handwritten character recognition,” Arab J Sci Eng, vol. 46, Jun. 2021, doi: 10.1007/s13369-021-05471-4.
S. K. and B. Bajpai Ashutosh and Wupadrasta, “Comparative Study of Faster Region-Based Convolutional Neural Networks with Inception V2 and Single Shot Detector with Inception V2 on Their Signature Detection Capabilities,” in Proceedings of International Conference on Big Data, Machine Learning and Applications, S. and B. V. E. Patgiri Ripon and Bandyopadhyay, Ed., Singapore: Springer Singapore, 2021, pp. 227–240. doi: https://doi.org/10.1007/978-981-33-4788-5_19.
J. Yang, P. Ren, and X. Kong, “Handwriting Text Recognition Based on Faster R-CNN,” in 2019 Chinese Automation Congress (CAC), 2019, pp. 2450–2454. doi: 10.1109/CAC48633.2019.8997382.
D. Made Sri Arsa, G. Agung Ayu Putri, R. Zen, and S. Bressan, “Isolated Handwritten Balinese Character Recognition from Palm Leaf Manuscripts with Residual Convolutional Neural Networks,” in 2020 12th International Conference on Knowledge and Systems Engineering (KSE), 2020, pp. 224–229. doi: 10.1109/KSE50997.2020.9287584.
A. Botalb, M. Moinuddin, U. M. Al-Saggaf, and S. S. A. Ali, “Contrasting Convolutional Neural Network (CNN) with Multi-Layer Perceptron (MLP) for Big Data Analysis,” in 2018 International Conference on Intelligent and Advanced System (ICIAS), 2018, pp. 1–5. doi: 10.1109/ICIAS.2018.8540626.
L. Alzubaidi et al., Review of deep learning: concepts, CNN architectures, challenges, applications, future directions, vol. 8, no. 1. Springer International Publishing, 2021. doi: 10.1186/s40537-021-00444-8.
S. Ren, K. He, R. Girshick, and J. Sun, “Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks,” IEEE Trans Pattern Anal Mach Intell, vol. 39, no. 6, pp. 1137–1149, 2017, doi: 10.1109/TPAMI.2016.2577031.
W. Li, “Analysis of Object Detection Performance Based on Faster R-CNN,” J Phys Conf Ser, vol. 1827, no. 1, p. 12085, Mar. 2021, doi: 10.1088/1742-6596/1827/1/012085.
R. Padilla, W. L. Passos, T. L. B. Dias, S. L. Netto, and E. A. B. Da Silva, “A comparative analysis of object detection metrics with a companion open-source toolkit,” Electronics (Switzerland), vol. 10, no. 3, pp. 1–28, Feb. 2021, doi: 10.3390/electronics10030279.
A. and M. R. and S. S. Srivastava Sharvani and Gangwar, “Sign Language Recognition System Using TensorFlow Object Detection API,” in Advanced Network Technologies and Intelligent Computing, S. K. and P. K. K. and V. A. and V. P. Woungang Isaac and Dhurandher, Ed., Cham: Springer International Publishing, 2022, pp. 634–646. doi: 10.48550/arXiv.2201.01486.
İ. Kılıç and G. Aydin, “Traffic Lights Detection and Recognition with New Benchmark Datasets Using Deep Learning and TensorFlow Object Detection API,” Traitement du Signal, vol. 39, pp. 1673–1683, Jun. 2022, doi: 10.18280/ts.390525.
Copyright (c) 2023 Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)
This work is licensed under a Creative Commons Attribution 4.0 International 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 ;
