Adversarial learning based attentional scene text recognizer
文献类型:期刊论文
作者 | Zhao, Jinyuan1,2; Wang, Yanna1; Xiao, Baihua1; Shi, Cunzhao1; Jiang, Jingzhong1,2; Wang, Chunheng1 |
刊名 | PATTERN RECOGNITION LETTERS |
出版日期 | 2020-10-01 |
卷号 | 138页码:217-222 |
ISSN号 | 0167-8655 |
关键词 | Scene text recognition Generative adversarial network Image rectification |
DOI | 10.1016/j.patrec.2020.07.027 |
通讯作者 | Xiao, Baihua(baihua.xiao@ia.ac.cn) |
英文摘要 | In this paper, we propose an adversarial learning based attentional scene text recognizer to solve the distortion problem of scene text image. We choose a rectification module which can rectify images in both horizontal and vertical directions, and use a recognizer based on the attention mechanism. Through the adversarial learning of the rectification network and the recognition network, we iteratively improve the rectification effect and the recognition performance. The entire network is trained with weak supervision, so only images and corresponding text labels are needed. Our method achieves high performance for both regular and irregular scene text images, and the experimental results tested on multiple benchmarks prove that our method achieves the performance of state-of-the-art. (C) 2020 Elsevier B.V. All rights reserved. |
WOS关键词 | NETWORK |
资助项目 | National Natural Science Foundation of China (NSFC)[61531019] ; National Natural Science Foundation of China (NSFC)[71621002] ; Key Programs of the Chinese Academy of Sciences[ZDBS-SSW-JSC003] ; Key Programs of the Chinese Academy of Sciences[ZDBS-SSW-JSC004] ; Key Programs of the Chinese Academy of Sciences[ZDBS-SSW-JSC005] |
WOS研究方向 | Computer Science |
语种 | 英语 |
出版者 | ELSEVIER |
WOS记录号 | WOS:000579804900030 |
资助机构 | National Natural Science Foundation of China (NSFC) ; Key Programs of the Chinese Academy of Sciences |
源URL | [http://ir.ia.ac.cn/handle/173211/42113] |
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 | Xiao, Baihua |
作者单位 | 1.Chinese Acad Sci CASIA, Inst Automat, 95 Zhongguancun East Rd, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci UCAS, 19 A Yuquan Rd, Beijing 100049, Peoples R China |
推荐引用方式 GB/T 7714 | Zhao, Jinyuan,Wang, Yanna,Xiao, Baihua,et al. Adversarial learning based attentional scene text recognizer[J]. PATTERN RECOGNITION LETTERS,2020,138:217-222. |
APA | Zhao, Jinyuan,Wang, Yanna,Xiao, Baihua,Shi, Cunzhao,Jiang, Jingzhong,&Wang, Chunheng.(2020).Adversarial learning based attentional scene text recognizer.PATTERN RECOGNITION LETTERS,138,217-222. |
MLA | Zhao, Jinyuan,et al."Adversarial learning based attentional scene text recognizer".PATTERN RECOGNITION LETTERS 138(2020):217-222. |
入库方式: OAI收割
来源:自动化研究所
浏览0
下载0
收藏0
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。