每年專案
摘要
Text recognition is an important task for extracting information from imagery data. Scene recognition is one of its challenging scenarios since characters may have diversified fonts or sizes, be occluded by other objects and be captured from varying angles or under different light conditions. In contrast to alpha-numerical characters, Traditional Chinese Characters (TCC) receive less attention and the large number of TCC makes it difficult to collect and label enough scene- images. This research aims at developing a set of strategies for TCC recognition. A synthetic dataset using a variety of data augmentation methods is constructed to simulate what may happen in real scenes, including deformations, noise adding and background changes. A segmentation-based spotting scheme is employed to locate the areas of -lines and single characters. The characters can be recognized by the trained model and then linked into meaningful -lines. The experimental results show that the proposed strategies work better in recognizing TCC in streetscape, when compared with existing publicly available tools.
原文 | ???core.languages.en_GB??? |
---|---|
主出版物標題 | 2021 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2021 - Proceedings |
發行者 | Institute of Electrical and Electronics Engineers Inc. |
頁面 | 1494-1498 |
頁數 | 5 |
ISBN(電子) | 9789881476890 |
出版狀態 | 已出版 - 2021 |
事件 | 2021 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2021 - Tokyo, Japan 持續時間: 14 12月 2021 → 17 12月 2021 |
出版系列
名字 | 2021 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2021 - Proceedings |
---|
???event.eventtypes.event.conference???
???event.eventtypes.event.conference??? | 2021 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2021 |
---|---|
國家/地區 | Japan |
城市 | Tokyo |
期間 | 14/12/21 → 17/12/21 |
指紋
深入研究「Strategies of Traditional Chinese Character Recognition in Streetscape Based on Deep Learning Networks」主題。共同形成了獨特的指紋。專案
- 2 已完成