Indonesian handwritten word segmentation using a neural word detector
DOI:
https://doi.org/10.35335/mandiri.v15i2.574Kata Kunci:
Deep Learning, Document Image, Indonesian Handwritten Recognition, Resnet, Word SegmentationAbstrak
Word segmentation is an essential preprocessing step in offline handwritten text recognition because accurate word localization directly affects subsequent recognition performance. This study presents an Indonesian handwritten word segmentation approach using a neural word detector designed to localize individual words in handwritten student assignment documents. The dataset consists of real handwritten student assignments, with word-level ground truth annotations manually created using LabelMe in the form of rectangular bounding boxes. A pretrained neural word detector was trained for five epochs and evaluated using an Intersection over Union (IoU) threshold of 0.50. Predicted word bounding boxes were matched with ground-truth boxes using the Hungarian assignment algorithm, with the matching cost defined from the IoU between corresponding boxes. Evaluation was conducted on 120 paired files containing 9,267 ground-truth word boxes and 9,308 evaluated predicted boxes. The detector achieved a precision of 92.35%, recall of 92.76%, and F1-score of 92.55%, while the mean IoU of matched bounding boxes reached 86.27%. These results indicate that the neural word detector can effectively localize handwritten Indonesian words with high detection consistency and spatial overlap. The study demonstrates the feasibility of neural word detection as a practical approach for word-level segmentation of real Indonesian handwritten documents. The resulting segmentation can provide localized word regions for subsequent handwritten word recognition and document analysis applications.
Referensi
Altwaijry, N., & Al-Turaiki, I. (2021). Arabic Handwriting Recognition System Using Convolutional Neural Network. Neural Computing and Applications, 33, 2249–2261. https://doi.org/10.1007/s00521-020-05070-8
Anju, A. T., Chacko, B. P., & Mohamed Basheer, K. P. (2024). Advancements in Segmentation of Unconstrained Malayalam Handwritten Documents for Enhanced OCR. Indian Journal of Science and Technology, 17(36), 3763–3775. https://doi.org/10.17485/IJST/v17i36.2220
Arbeláez, P., Maire, M., Fowlkes, C., & Malik, J. (2011). Contour Detection and Hierarchical Image Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(5), 898–916. https://doi.org/10.1109/TPAMI.2010.161
Axler, G., & Wolf, L. (2018). Toward a Dataset-Agnostic Word Segmentation Method. Proceedings of the IEEE International Conference on Image Processing (ICIP), 2635–2639. https://doi.org/10.1109/ICIP.2018.8451124
Berriche, L., Alqahtani, A., & Rekik, S. (2024). Hybrid Arabic Handwritten Character Segmentation Using CNN and Graph Theory Algorithm. Journal of King Saud University – Computer and Information Sciences, 36, 101872. https://doi.org/10.1016/j.jksuci.2023.101872
Boudraa, O., Michelucci, D., & Hidouci, W. K. (2022). PUNet: Novel and Efficient Deep Neural Network Architecture for Handwritten Documents Word Spotting. Pattern Recognition Letters, 155, 19–26. https://doi.org/10.1016/j.patrec.2022.01.019
Calvo-Zaragoza, J., & Gallego, A.-J. (2019). A selectional auto-encoder approach for document image binarization. Pattern Recognition, 86, 37–47. https://doi.org/10.1016/j.patcog.2018.08.011
de Sousa Neto, A. F., Bezerra, B. L. D., Duarte de Moura, G. C., & Toselli, A. H. (2024). Data Augmentation for Offline Handwritten Text Recognition: A Systematic Literature Review. SN Computer Science, 5, 258. https://doi.org/10.1007/s42979-023-02583-6
Dhiaf, M., Cheikh Rouhou, A., Kessentini, Y., & Ben Salem, S. (2023). MSdocTr-Lite: A Lite Transformer for Full Page Multi-Script Handwriting Recognition. Pattern Recognition Letters, 169, 28–34. https://doi.org/10.1016/j.patrec.2023.03.020
Diem, M., Kleber, F., Fiel, S., Grüning, T., & Gatos, B. (2017). cBAD: ICDAR2017 competition on baseline detection. 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), 1, 1355–1360. https://doi.org/10.1109/ICDAR.2017.222
Elkhayati, M., Elkettani, Y., & Mourchid, M. (2022). Segmentation of Handwritten Arabic Graphemes Using a Directed Convolutional Neural Network and Mathematical Morphology Operations. Pattern Recognition, 122, 108288. https://doi.org/10.1016/j.patcog.2021.108288
Grüning, T., Labahn, R., Diem, M., Kleber, F., & Fiel, S. (2018). READ-BAD: A Dataset and Evaluation Scheme for Baseline Detection in Archival Documents. International Conference on Document Analysis and Recognition (ICDAR). https://doi.org/10.1109/ICDAR.2017.307
Hand, D. J., Christen, P., & Kirielle, N. (2021). F*: An Interpretable Transformation of the F-Measure. Machine Learning, 110(3), 451–456. https://doi.org/10.1007/s10994-021-05964-1
He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep Residual Learning for Image Recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 770–778. https://doi.org/10.1109/CVPR.2016.90
He, S., & Schomaker, L. (2019). DeepOtsu: Document enhancement and binarization using iterative deep learning. Pattern Recognition, 91, 379–390. https://doi.org/10.1016/j.patcog.2019.01.025
Hu, S.-Y., Wang, Q.-F., Huang, K., Wen, M., & Coenen, F. (2022). Retrieval-Based Language Model Adaptation for Handwritten Chinese Text Recognition. International Journal on Document Analysis and Recognition, 26, 109–119. https://doi.org/10.1007/s10032-022-00419-2
Jindal, A., & Ghosh, R. (2023). Word and Character Segmentation in Ancient Handwritten Documents in Devanagari and Maithili Scripts Using Horizontal Zoning. Expert Systems with Applications, 225, 120127. https://doi.org/10.1016/j.eswa.2023.120127
Kang, L., Riba, P., Rusiñol, M., Fornés, A., & Villegas, M. (2022). Pay Attention to What You Read: Non-Recurrent Handwritten Text-Line Recognition. Pattern Recognition, 129, 108766. https://doi.org/10.1016/j.patcog.2022.108766
Kaur, R., Rani, R., & Pahuja, R. (2025). LUNet: Lightweight U-Net with adaptive scaling for Devanagari handwritten word segmentation. Engineering Applications of Artificial Intelligence, 159, 111618. https://doi.org/10.1016/j.engappai.2025.111618
Kingma, D. P., & Ba, J. (2015). Adam: A Method for Stochastic Optimization. International Conference on Learning Representations (ICLR). https://arxiv.org/abs/1412.6980
López, P., Zubasti, P., García, J., & Molina, J. M. (2026). A UAV-Based Framework for Visual Detection and Geospatial Mapping of Real Road Surface Defects. Drones, 10(2), 119. https://doi.org/10.3390/drones10020119
Nikolaidou, K., Seuret, M., Mokayed, H., & Liwicki, M. (2022). A Survey of Historical Document Image Datasets. International Journal on Document Analysis and Recognition, 25, 305–338. https://doi.org/10.1007/s10032-022-00405-8
Oliveira, S. A., Seguin, B., & Kaplan, F. (2018). dhSegment: A generic deep-learning approach for document segmentation. 2018 16th International Conference on Frontiers in Handwriting Recognition (ICFHR), 7–12. https://doi.org/10.1109/ICFHR-2018.2018.00011
Pravalpruk, B., & Dailey, M. N. (2024). Deep Handwritten Diagram Segmentation. IET Image Processing, 18(13), 4207–4220. https://doi.org/10.1049/ipr2.13243
Quirós, L., & Vidal, E. (2022). Reading Order Detection on Handwritten Documents. Neural Computing and Applications, 34, 9593–9611. https://doi.org/10.1007/s00521-022-06948-5
Rakshit, P., Halder, C., Sk, M. O., & Roy, K. (2023). A Generalized Line Segmentation Method for Multi-Script Handwritten Text Documents. Expert Systems with Applications, 212, 118498. https://doi.org/10.1016/j.eswa.2022.118498
Ronneberger, O., Fischer, P., & Brox, T. (2015). U-Net: Convolutional Networks for Biomedical Image Segmentation. Medical Image Computing and Computer-Assisted Intervention (MICCAI), 234–241. https://doi.org/10.1007/978-3-319-24574-4_28
Russell, B. C., Torralba, A., Murphy, K. P., & Freeman, W. T. (2008). LabelMe: A Database and Web-Based Tool for Image Annotation. International Journal of Computer Vision, 77, 157–173. https://doi.org/10.1007/s11263-007-0090-8
Saloum, S. S., & García-Magariño, I. (2021). Algorithm Based on Normal Coordinate Vectors with 16 Segments for the Data Fusion from Hand-Written Arabic Text Implemented with MATLAB. PeerJ Computer Science, 7, e705. https://doi.org/10.7717/peerj-cs.705
Shivakumara, P., Jain, T., Pal, U., Surana, N., Antonacopoulos, A., & Lu, T. (2022). Text Line Segmentation from Struck-Out Handwritten Document Images. Expert Systems with Applications, 210, 118266. https://doi.org/10.1016/j.eswa.2022.118266
Tüselmann, O., & Fink, G. A. (2024). Neural Models for Semantic Analysis of Handwritten Document Images. International Journal on Document Analysis and Recognition, 27, 245–263. https://doi.org/10.1007/s10032-024-00477-8
Wibowo, M. A., Soleh, M., Pradani, W., Hidayanto, A. N., & Arymurthy, A. M. (2017). Handwritten Javanese Character Recognition Using Discriminative Deep Learning Technique. 2017 2nd International Conference on Information Technology, Information Systems and Electrical Engineering (ICITISEE), 325–330. https://doi.org/10.1109/ICITISEE.2017.8285521
Wolf, F., & Fink, G. A. (2024). Self-Training for Handwritten Word Recognition and Retrieval. International Journal on Document Analysis and Recognition, 27, 225–244. https://doi.org/10.1007/s10032-024-00484-9
Wu, H., Du, C., Ji, Z., Gao, M., & He, Z. (2021). SORT-YM: An Algorithm of Multi-Object Tracking with YOLOv4-Tiny and Motion Prediction. Electronics, 10(18), 2319. https://doi.org/10.3390/electronics10182319
Zhou, X., Yao, C., Wen, H., Wang, Y., Zhou, S., He, W., & Liang, J. (2017). EAST: An Efficient and Accurate Scene Text Detector. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 5551–5560. https://doi.org/10.1109/CVPR.2017.283
Unduhan
Diterbitkan
Cara Mengutip
Terbitan
Bagian
Lisensi
Hak Cipta (c) 2026 Zulkarnaen Hatala
Artikel ini berlisensi Creative Commons Attribution-NonCommercial 4.0 International License.
