Handwritten Hiragana Letter Detection Using CNN

Arya Fernandi - Telkom University, Jalan Telekomunikasi No.1, Bandung, Indonesia
Sofia Sa'idah - Telkom University, Jalan Telekomunikasi No.1, Bandung, Indonesia
Rita Magdalena - Telkom University, Jalan Telekomunikasi No.1, Bandung, Indonesia


Citation Format:



DOI: http://dx.doi.org/10.62527/joiv.8.3-2.3035

Abstract


Hiragana is one of the primary alphabets used in Japanese. Hiragana is a phonetic symbol; each letter represents one syllable. Hiragana letters are formed from curved lines and strokes. However, detecting Hiragana letters causes many errors because people still rely on their vision to detect the letters, especially people familiar with them for the first time. It will be difficult and not very clear to read the letters. Therefore, a Convolutional Neural Network (CNN) method is used to detect handwritten Hiragana letters and help people who first get to know Hiragana letters when the letters are too complicated for human eyes to detect. This research uses the YOLOv8 model as a handwritten Hiragana letter detection algorithm. The Hiragana letters to be detected are basic letters with 46 characters. This research uses the YOLOv8 model run on Google Collaboratory with the Ultralytics library version 8.0.20 using the Python programming language. The dataset is collected from the internet and annotated using the Roboflow framework and dataset 4600 Hiragana letters. From the test results, the best model is YOLOv8l using SGD optimizer and learning rate 0.01 with a precision value of 98.5%, recall value of 95.7%, f1-score value of 97.1%, and mAP value of 95.5%. In the future, we aim to expand the number of datasets and employ a broader range of hyperparameter values to optimize the classification precision and accuracy of the Hiragana Letter Detection system.


Keywords


Hiragana Characters, YOLOv8; Convolutional Neural Network (CNN); Python; mAP; Recall; F1score; precission.

Full Text:

PDF

References


A. H. Mawaddah, C. A. Sari, D. R. I. M. Setiadi, and E. H. Rachmawanto. (2020). Handwriting Recognition of Hiragana Characters using Convolutional Neural Network. 2020 International Seminar on Application for Technology of Information and Communication (iSemantic). https://doi.org/10.1109/isemantic50169.2020.9234211.

N. E. W. Nugroho and A. Harjoko.(2021). Transliteration of Hiragana and Katakana handwritten characters using CNN-SVM. IJCCS (Indonesian Journal of Computing and Cybernetics Systems),15(3). https://doi.org/10.22146/ijccs.66062.

C. Umam, A. D. Krismawan, and R. R. Ali. (2021). CNN for Image Identification of Hiragana Based on Pattern Recognition using CNN. Journal of Applied Intelligent System, 6(2), 62–71. https://doi.org/ 10.33633/jais.v6i2.4586.

Tamang, S., Sen, B., Pradhan, A., Sharma, K., & Singh, V. K. (2023). Exploring YOLOv8 Object Detection for Accurate Face Mask Classification. Ijisae, 2023(2), 892–897. www.ijisae.org.

Taye, M. M. (2023). Understanding of Machine Learning with Deep Learning: Architectures, Workflow, Applications and Future Directions. Computers, 12(5). https://doi.org/10.3390/computers12050091.

Sarker, I. H. (2021). Deep Learning: A Comprehensive Overview on Techniques, Taxonomy, Applications and Research Directions. SN Computer Science, 2(6), 1–20. https://doi.org/10.1007/s42979-021-00815-1

K. Kaplan, Y. Kaya, M. Kuncan, and H. M. Ertunç.(2020). Brain tumor classification using modified local binary patterns (LBP) feature extraction methods. Medical Hypotheses, 139. https:// doi.org/ 10.1016/j.mehy.2020.109696.

Nissa. Novia Farhan, Jamiati. Angelia, Cahya. Nilam, Anton, and Astuti. Puji. (2021). Application of Deep Learning using Convolutional Neural Network (CNN) Method for Women’s Skin Calssification”. Scientific Journal of Informatics, 8(1). https:// doi.org/10.15294/sji.v8il.26888.

Suwitono, Y. A., & Kaunang, F. J. (2022). Implementasi Algoritma Convolutional Neural Network (CNN) Untuk Klasifikasi Daun Dengan Metode Data Mining SEMMA Menggunakan Keras. Jurnal Komtika (Komputasi Dan Informatika), 6(2), 109–121. https://doi.org/10.31603/komtika.v6i2.8054.

Elsayed. Mahmoud Said, Jahromi. Hamed, Nazir, Mohsin and Jurcut, Anca D.(2021). The role of CNN for Intrusion Detection Systems : An Improved CNN Learning Approach for SDNs. 5th EAI International Conference on Future Access Enablers of Ubiquitous and Intelligent Infrastructure.

Alantali, F., Halawani, Y., Mohammad, B., & Al-Qutayri, M. (2021). SLID: Exploiting Spatial Locality in Input Data as a Computational Reuse Method for Efficient CNN. IEEE Access, 9, 57179–57187. https://doi.org/10.1109/ACCESS.2021.3071409

A. R. Fauzy. (2019). Implementasi Metode Region Convolutional Neural Network Dalam Mendiagnosa Anomali Pneumonia Pada Foto Thorax - Elibrary Unikom. Unikom.ac.id.

R. B. J. Simanjuntak, Y. Fua’dah, R. Magdalena, S. Saidah, A. B. Wiratama, and I. D. S. Ubaidah. (2022). Cataract classification based on FundUs images using convolutional neural network. JOIV International Journal on Informatics Visualization, 6(1), 33,. https://doi.org/10.30630/joiv.6.1.856.

Cutting, V., & Stephen, N. (2021). A Review on Using Python as A Preferred Programming Language for Beginners. International Research Journal of Engineering and Technology, 8(8), 4258–4263. https://www.irjet.net/archives/V8/i8/IRJET-V8I8505.pdf

J. Terven and D. Cordova-Esparza. (2023). A comprehensive review of YOLO architectures in computer vision: from YOLOV1 to YOLOV8 and YOLO-NAS,” arXiv (Cornell University),. https://doi.org/10.48550/arxiv.2304.00501.

Panja, E., & Dewi, C. (2024). YOLOv8 Analysis for Vehicle Classification Under Various Image Conditions. Scientific Journal of Informatics, 11(1), 127–138. https://doi.org/10.15294/sji.v11i1.49038.

Xu, Q. I., Wei, Y., Gao, J. I. E., & Yao, H. (2023). ICAPD Framework and simAM-YOLOv8n for Student Cognitive Engagement Detection in Classroom. IEEE Access 11, 136063–136076. https://doi.org/10.1109/ACCESS.2023.3337435.

Kimeu, J. M., Kisangiri, M., Mbelwa, H., & Leo, J. (2024). Informatics in Medicine Unlocked Deep learning-based mobile application for the enhancement of pneumonia medical imaging analysis: A case-study of West-Meru Hospital. Informatics in Medicine Unlocked, 50, 101582. https://doi.org/10.1016/j.imu.2024.101582.

June, V. N., Ali, U., Ismail, M. A., Ahamed, R., Habeeb, A., Roshaan, S., & Shah, A. (2024). Performance Evaluation of YOLO Models in Plant Disease Detection. J. Informatics Web Eng., 3(2), 199–211. https:// doi.org/10.33093/jiwe.2024.3.2.15.

P.-W. Chin, K.-W. Ng, and N. Palanichamy. (2024). Plant Disease Detection and Classification Using Deep Learning Methods: A Comparison Study. J. Informatics Web Eng., 3(1), 155–168, 2024. https://doi.org/10.33093/jiwe.2024.3.1.10.

K. Chromiński, Ľ. Benko, Z. J. Hernández-Figueroa, J. D. González-Domínguez, and J. C. Rodríguez-del-Pino. (2021). Python Fundamentals. Python Fundam. https://doi.org/10.17846/fpvai-2021-14

M. S. Z. Ahmad, N. A. Ab. Aziz, and A. K. Ghazali. (2024). Development of Automated Attendance System Using Pretrained Deep Learning Models. Int. J. Robot. Autom. Sci, 6(1), 6–12. https://doi.org/10.33093/ijoras.2024.6.1.2.

Solanellas, P. G. (2022). Designing Convolutional Neural Networks for Classification of Metastatic Tissue in the Lymph Nodes. Available:

https://www.diva-portal.org/smash/get/diva2:1703302/FULLTEXT01.pdf

Y. Sun, B. Xue, M. Zhang, and G. G. Yen. (2020). Completely Automated CNN Architecture Design Based on Blocks. IEEE Transactions on Neural Networks and Learning Systems, 31(4), 1242-1254.https:// doi.org/ 10.1109/TNNLS.2019.2919608.

Agastya, W., & Huda, S. (2023). Multichannel Convolutional Neural Network Model to Improve Compound Emotional Text Classification Performance. IAENG International Journal of Computer Science 50(3).

Zafar, A., Aamir, M., Nawi, N. M., Arshad, A., Riaz, S., Alruban, A., Dutta, A. K., & Almotairi, S. (2022). A Comparison of Pooling Methods for Convolutional Neural Networks. Applied Science, 12(17), 8643. https://doi.org/10.3390/app12178643

H. Kunert. (2020). Contemporary Loanwords in hiragana: An Analysis of Typical Traits and Contexts. Japanese Stud, 40(1), 21–40. https://doi.org/10.1080/10371397.2019.1682935.

D. Krstinić, M. Braović, L. Šerić, and D. Božić-Štulić. (2020). Multi-label Classifier Performance Evaluation with Confusion Matrix.CSCP, 01–14. https://doi.org/10.5121/csit.2020.100801.

S. Jiang, T. Xu, J. Li, B. Huang, J. Guo, and Z. Bian. (2019). IdentifyNet for non-maximum suppression. IEEE Access,7, 148245–148253. https://doi.org/10.1109/ACCESS.2019.2944671.

Y. Sun, B. Xue, M. Zhang, G. G. Yen, and J. Lv. (2020). Automatically Designing CNN Architectures Using the Genetic Algorithm for Image Classification. IEEE Transactions on Cybernetics, 50(9), 3840-3854. https://doi.org/10.1109/TCYB.2020.2983860.

Helmy. Maged, Truong, Trung Tuyen, Jul, Eric and Ferreira. Paulo. (2023). Deep Learning and computer vision techniques for microcirculation analysis: A review. Patterns. https://doi.org/10.1016/j.patter.2022.100641