| Autor: |
Wenjun Xiao, Shanxiong Chen, Yuqi Ma, Yongbo Li, Xiaolong Wang, Yaoyao Feng, Weizheng Qiao, Xun Pu |
| Jazyk: |
angličtina |
| Rok vydání: |
2024 |
| Předmět: |
|
| Zdroj: |
Heritage Science, Vol 12, Iss 1, Pp 1-12 (2024) |
| Druh dokumentu: |
article |
| ISSN: |
2050-7445 |
| DOI: |
10.1186/s40494-024-01489-7 |
| Popis: |
Abstract Recognizing online handwriting Yi text is crucial for recording and preserving Yi literature. However, the scarcity of online handwriting Yi text datasets has limited relevant research, impeding the process of Yi informatization. In this work, we use synthetic data to train models, and an Online Handwriting Yi Text Recognition Network (YTRN) is proposed, which extracts robust character features to address the gap between synthetic and real data. YTRN adeptly learns the spatial structure features from path signature feature maps and captures trajectory features from the pen-tip trajectories. Subsequently, an innovative adaptive feature fusion module integrates these two sets of features to yield more comprehensive and robust character representations. Experiments on our newly collected Yi-OLHWDB2.0 dataset demonstrate that our method outperforms previous approaches, achieving an impressive 95.67% accuracy. This highlights the model’s effectiveness in extracting comprehensive and robust features from path signature maps and pen-tip trajectories, significantly enhancing recognition accuracy and generalization. |
| Databáze: |
Directory of Open Access Journals |
| Externí odkaz: |
|
|
Nepřihlášeným uživatelům se plný text nezobrazuje |
K zobrazení výsledku je třeba se přihlásit.
|
