OSTER: An Orientation Sensitive Scene Text Recognizer with CenterLine Rectification
文献类型:会议论文
作者 | Zipeng Feng1,2; Chen Du1,2; Yanna Wang2; Baihua Xiao2; Xiao, Baihua![]() ![]() ![]() ![]() |
出版日期 | 2020-02 |
会议日期 | 2019.11.26-2019.11.29 |
会议地点 | Auckland, New Zealand |
关键词 | Scene text recognition Arbitrarily-aligned Chinese texts Attention selective network Centerline rectification Sequence-to-sequence |
页码 | 483-497 |
英文摘要 |
Scene texts in China are always arbitrarily arranged in two forms: horizontally and vertically. These two forms of texts exhibit distinctive features, making it difficult to recognize them simultaneously. Besides, recognizing irregular scene texts is still a challenging task due to their various shapes and distorted patterns. In this paper, we propose an orientation sensitive network aiming at distinguishing between Chinese horizontal and vertical texts. The learned orientation is then passed into an attention selective network to adjust the attention maps of the sequence recognition model, leading it working for each type of texts respectively. In addition, a lightweight centerline rectification network is adopted, which enables the irregular texts more readable while no redundant labels are needed. A synthetic dataset named SCTD is released to support our training and evaluate the proposed model. Extensive experiments show that the proposed method is capable of recognizing arbitrarily-aligned scene texts accurately and efficiently, achieving |
语种 | 英语 |
源URL | [http://ir.ia.ac.cn/handle/173211/39244] ![]() |
专题 | 自动化研究所_复杂系统管理与控制国家重点实验室_影像分析与机器视觉团队 |
通讯作者 | Baihua Xiao; Xiao, Baihua |
作者单位 | 1.中国科学院大学 2.中科院自动化研究所 |
推荐引用方式 GB/T 7714 | Zipeng Feng,Chen Du,Yanna Wang,et al. OSTER: An Orientation Sensitive Scene Text Recognizer with CenterLine Rectification[C]. 见:. Auckland, New Zealand. 2019.11.26-2019.11.29. |
入库方式: OAI收割
来源:自动化研究所
其他版本
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。