A Text Localization Method Based on Weak Supervision | |
Zhang, Jiyuan1,2; Du, Chen1,2; Feng, Zipeng1,2; Wang, Yanna1; Wang, Chunheng1 | |
2020-02-03 | |
会议名称 | 2019 International Conference on Document Analysis and Recognition (ICDAR) |
会议日期 | 20-25 Sept. 2019 |
会议地点 | Sydney, Australia, Australia |
出版者 | IEEE |
摘要 | Recently, numerous deep learning based scene text detection methods have achieved promising performances in different text detecting tasks. Most of these methods are trained in a supervised way, which requires a large amount of annotated data. In this paper, we explore a weakly supervised method to locate text regions in scene images. We propose a fully convolutional network (FCN) architecture to implement binary classification. The training data we used do not need any text location annotation, we only need to divide the training data into two categories according to whether it contains text or not. We can obtain the text localization map (TLM) directly from the last convolutional layer. By setting a fixed threshold, the TLM is converted to a mask map. Then the connected component analysis and the text proposals method based on Maximally Stable Extremal Regions (MSERs) are used to get the text region bounding boxes. We conduct comprehensive experiments on standard text datasets. The results show that our text localization method achieves comparable recall performance with other methods and has more stable property. |
关键词 | weak supervision fully convolutional network text localization map |
DOI | 10.1109/ICDAR.2019.00129 |
收录类别 | EI |
语种 | 英语 |
七大方向——子方向分类 | 文字识别与文档分析 |
引用统计 | |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/39227 |
专题 | 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 |
通讯作者 | Wang, Chunheng |
作者单位 | 1.Institute of Automation, Chinese Academy of Sciences 2.University of Chinese Academy of Sciences |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Zhang, Jiyuan,Du, Chen,Feng, Zipeng,et al. A Text Localization Method Based on Weak Supervision[C]:IEEE,2020. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
08978173.pdf(1179KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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