Knowledge Commons of Institute of Automation,CAS
Towards open-set text recognition via label-to-prototype learning | |
Liu, Chang1; Yang, Chun1; Qin, Hai-Bo1; Zhu, Xiaobin1; Liu, Cheng-Lin2; Yin, Xu-Cheng1 | |
发表期刊 | PATTERN RECOGNITION |
ISSN | 0031-3203 |
2023-02-01 | |
卷号 | 134页码:13 |
通讯作者 | Yang, Chun(chunyang@ustb.edu.cn) ; Yin, Xu-Cheng(xuchengyin@ustb.edu.cn) |
摘要 | Scene text recognition is a popular research topic which is also extensively utilized in the industry. Al-though many methods have achieved satisfactory performance for the close-set text recognition chal-lenges, these methods lose feasibility in open-set scenarios, where collecting data or retraining models for novel characters could yield a high cost. For example, annotating samples for foreign languages can be expensive, whereas retraining the model each time when a "novel" character is discovered from historical documents costs both time and resources. In this paper, we introduce and formulate a new open-set text recognition task which demands the capability to spot and recognize novel characters without retrain-ing. A label-to-prototype learning framework is also proposed as a baseline for the new task. Specifically, the framework introduces a generalizable label-to-prototype mapping function to build prototypes (class centers) for both seen and unseen classes. An open-set predictor is then utilized to recognize or reject samples according to the prototypes. The implementation of rejection capability over out-of-set charac-ters allows automatic spotting of unknown characters in the incoming data stream. Extensive experiments show that our method achieves promising performance on a variety of zero-shot, close-set, and open-set text recognition datasets. (c) 2022 Elsevier Ltd. All rights reserved. |
关键词 | Open-set recognition Scene text recognition Low-shot recognition |
DOI | 10.1016/j.patcog.2022.109109 |
关键词[WOS] | NETWORK ; CLASSIFICATION |
收录类别 | SCI |
语种 | 英语 |
资助项目 | National Key Research and Development Program of China ; National Science Fund for Distinguished Young Scholars ; National Natural Science Foundation of China ; [2020AAA09701] ; [62125601] ; [62006018] ; [62076024] |
项目资助者 | National Key Research and Development Program of China ; National Science Fund for Distinguished Young Scholars ; National Natural Science Foundation of China |
WOS研究方向 | Computer Science ; Engineering |
WOS类目 | Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic |
WOS记录号 | WOS:000880031000003 |
出版者 | ELSEVIER SCI LTD |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/50700 |
专题 | 多模态人工智能系统全国重点实验室_模式分析与学习 |
通讯作者 | Yang, Chun; Yin, Xu-Cheng |
作者单位 | 1.Univ Sci & Technol Beijing, Sch Comp & Commun Engn, Dept Comp Sci & Technol, Beijing 100083, Peoples R China 2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China |
推荐引用方式 GB/T 7714 | Liu, Chang,Yang, Chun,Qin, Hai-Bo,et al. Towards open-set text recognition via label-to-prototype learning[J]. PATTERN RECOGNITION,2023,134:13. |
APA | Liu, Chang,Yang, Chun,Qin, Hai-Bo,Zhu, Xiaobin,Liu, Cheng-Lin,&Yin, Xu-Cheng.(2023).Towards open-set text recognition via label-to-prototype learning.PATTERN RECOGNITION,134,13. |
MLA | Liu, Chang,et al."Towards open-set text recognition via label-to-prototype learning".PATTERN RECOGNITION 134(2023):13. |
条目包含的文件 | 条目无相关文件。 |
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。
修改评论