Main Article Content
Abstract
Handwritten character recognition is one of the challenges in the field of digital image processing, especially in academic documents such as thesis guidance minutes. This study aims to compare the performance of the YOLOv8 model in detecting handwritten characters on two types of datasets, namely original images and preprocessed images. Preprocessing is carried out through the stages of grayscale, CLAHE, Gaussian blur, adaptive thresholding Gaussian, dilation, and erosion. Labels in the preprocessed data are obtained by copying annotations from the original data without adjusting for visual changes. Both datasets were trained using YOLOv8s for 30 epochs. The evaluation results show that the model trained on the original data gives the best results with mAP@0.5 of 0.795 and mAP@0.5:0.95 of 0.606, while the model trained on the preprocessed data only achieves mAP@0.5 of 0.748 and mAP@0.5:0.95 of 0.560.
Keywords
Article Details
References
- Azizah, A. N. , F. C. (2023). Tajweed-YOLO: Object Detection Method for Tajweed by Applying HSV Color Model Augmentation on Mushaf Images. Jurnal RESTI (Rekayasa Sistem Dan Teknologi Informasi), 7(2). https://doi.org/10.29207/resti.v7i2.4739
- Geetha, R., Thilagam, T., & Padmavathy, T. (2021). Effective offline handwritten text recognition model based on a sequence-to-sequence approach with CNN–RNN net-works. In Neural Computing and Applica-tions (Vol. 33, Issue 17). https://doi.org/10.1007/s00521-020-05556-5
- Kamboj, D., Dipanjali, Mittal, A., Tiwari, A., & Agarwal, D. (2024). DigiSketch: Automat-ing the Conversion of Hand-Drawn Dia-grams to Digital. Proceedings of Interna-tional Conference on Communication, Com-puter Sciences and Engineering, IC3SE 2024, 354–358. https://doi.org/10.1109/IC3SE62002.2024.10592887
- Kusetogullari, H., Yavariabdi, A., Hall, J., & Lavesson, N. (2021). DIGITNET: A Deep Handwritten Digit Detection and Recogni-tion Method Using a New Historical Handwritten Digit Dataset. Big Data Re-search, 23. https://doi.org/10.1016/j.bdr.2020.100182
- Mahadevkar, S., Patil, S., & Kotecha, K. (2024). Enhancement of handwritten text recogni-tion using AI-based hybrid approach. MethodsX, 12. https://doi.org/10.1016/j.mex.2024.102654
- Redmon, J., Divvala, S., Girshick, R., & Far-hadi, A. (2016). You only look once: Uni-fied, real-time object detection. Proceed-ings of the IEEE Computer Society Confer-ence on Computer Vision and Pattern Recognition, 2016-December, 779–788. https://doi.org/10.1109/CVPR.2016.91
- Solawetz, J., & Francesco. (2023). What is YOLOv8? The Ultimate Guide. Roboflow. https://blog.roboflow.com/whats-new-in-yolov8/
- Suciati, N., Sutramiani, N. P., & Siahaan, D. (2022). LONTAR-DETC: Dense and High Variance Balinese Character Detection Method in Lontar Manuscripts. IEEE Ac-cess, 10, 14600–14609. https://doi.org/10.1109/ACCESS.2022.3147069
- Sutramiani, N. P., Suciati, N., & Siahaan, D. (2021). MAT-AGCA: Multi Augmentation Technique on small dataset for Balinese character recognition using Convolutional Neural Network. ICT Express, 7(4), 521–529. https://doi.org/10.1016/j.icte.2021.04.005
- Varshini, C., Yogeshwaran, S., & Mekala, V. (2024). Tamil and English Handwritten Character Segmentation and Recognition Using Deep Learning. 2024 International Conference on Communication, Computing and Internet of Things, IC3IoT 2024 - Pro-ceedings. https://doi.org/10.1109/IC3IoT60841.2024.10550221
References
Azizah, A. N. , F. C. (2023). Tajweed-YOLO: Object Detection Method for Tajweed by Applying HSV Color Model Augmentation on Mushaf Images. Jurnal RESTI (Rekayasa Sistem Dan Teknologi Informasi), 7(2). https://doi.org/10.29207/resti.v7i2.4739
Geetha, R., Thilagam, T., & Padmavathy, T. (2021). Effective offline handwritten text recognition model based on a sequence-to-sequence approach with CNN–RNN net-works. In Neural Computing and Applica-tions (Vol. 33, Issue 17). https://doi.org/10.1007/s00521-020-05556-5
Kamboj, D., Dipanjali, Mittal, A., Tiwari, A., & Agarwal, D. (2024). DigiSketch: Automat-ing the Conversion of Hand-Drawn Dia-grams to Digital. Proceedings of Interna-tional Conference on Communication, Com-puter Sciences and Engineering, IC3SE 2024, 354–358. https://doi.org/10.1109/IC3SE62002.2024.10592887
Kusetogullari, H., Yavariabdi, A., Hall, J., & Lavesson, N. (2021). DIGITNET: A Deep Handwritten Digit Detection and Recogni-tion Method Using a New Historical Handwritten Digit Dataset. Big Data Re-search, 23. https://doi.org/10.1016/j.bdr.2020.100182
Mahadevkar, S., Patil, S., & Kotecha, K. (2024). Enhancement of handwritten text recogni-tion using AI-based hybrid approach. MethodsX, 12. https://doi.org/10.1016/j.mex.2024.102654
Redmon, J., Divvala, S., Girshick, R., & Far-hadi, A. (2016). You only look once: Uni-fied, real-time object detection. Proceed-ings of the IEEE Computer Society Confer-ence on Computer Vision and Pattern Recognition, 2016-December, 779–788. https://doi.org/10.1109/CVPR.2016.91
Solawetz, J., & Francesco. (2023). What is YOLOv8? The Ultimate Guide. Roboflow. https://blog.roboflow.com/whats-new-in-yolov8/
Suciati, N., Sutramiani, N. P., & Siahaan, D. (2022). LONTAR-DETC: Dense and High Variance Balinese Character Detection Method in Lontar Manuscripts. IEEE Ac-cess, 10, 14600–14609. https://doi.org/10.1109/ACCESS.2022.3147069
Sutramiani, N. P., Suciati, N., & Siahaan, D. (2021). MAT-AGCA: Multi Augmentation Technique on small dataset for Balinese character recognition using Convolutional Neural Network. ICT Express, 7(4), 521–529. https://doi.org/10.1016/j.icte.2021.04.005
Varshini, C., Yogeshwaran, S., & Mekala, V. (2024). Tamil and English Handwritten Character Segmentation and Recognition Using Deep Learning. 2024 International Conference on Communication, Computing and Internet of Things, IC3IoT 2024 - Pro-ceedings. https://doi.org/10.1109/IC3IoT60841.2024.10550221