| dc.contributor | 華文碩 | |
| dc.creator (作者) | 杜容玥 | |
| dc.creator (作者) | Tu, Jung-Yueh | |
| dc.creator (作者) | Chen, Tingzhu | |
| dc.creator (作者) | Qian, Yaoyao | |
| dc.creator (作者) | Pei, Jingyu | |
| dc.creator (作者) | Wu, Shaoteng | |
| dc.creator (作者) | Wu, Jiang | |
| dc.creator (作者) | Li, Lin | |
| dc.date (日期) | 2020-12 | |
| dc.date.accessioned | 28-Mar-2022 15:31:03 (UTC+8) | - |
| dc.date.available | 28-Mar-2022 15:31:03 (UTC+8) | - |
| dc.date.issued (上傳時間) | 28-Mar-2022 15:31:03 (UTC+8) | - |
| dc.identifier.uri (URI) | http://nccur.lib.nccu.edu.tw/handle/140.119/139459 | - |
| dc.description.abstract (摘要) | Oracle bone script recognition (OBSR) has been a fundamental problem in research on oracle bone scripts for decades. Despite being intensively studied, existing OBSR methods are still subject to limitations regarding recognition accuracy, speed and robustness. Furthermore, the dependency of these methods on expert knowledge hinders the adoption of OBSR systems by the general public and also discourages social outreach of research outputs. Addressing these issues, this study proposes an encoding-based OBSR system that applies image pre-processing techniques to encode oracle images into small matrices and recognize oracle characters in the encoding space. We tested our methods on a collection of oracle bones from the Yin Ruins in XiaoTun village, and achieved a high accuracy rate of 99% within a time range of milliseconds. | |
| dc.format.extent | 121 bytes | - |
| dc.format.mimetype | text/html | - |
| dc.relation (關聯) | Journal of Chinese Writing Systems,Vol.4, No.4, pp.281-290 | |
| dc.subject (關鍵詞) | Encoding-based;oracle bone script;recognition technology;relevant information points;XiaoTun village | |
| dc.title (題名) | A study on encoding-based oracle bone script recognition | |
| dc.type (資料類型) | article | |
| dc.identifier.doi (DOI) | 10.1177/2513850220952890 | |
| dc.doi.uri (DOI) | https://doi.org/doi: 10.1177/2513850220952890 | |
