Single shot multi-oriented text detection based on local and non-local features | |
Li, XiaoQian1,2![]() ![]() ![]() ![]() ![]() | |
发表期刊 | INTERNATIONAL JOURNAL ON DOCUMENT ANALYSIS AND RECOGNITION
![]() |
ISSN | 1433-2833 |
2020-08-04 | |
期号 | 2020页码:241-252 |
摘要 | In order to improve the robustness of text detector on scene text of various scales, a single shot text detector that combines local and non-local features is proposed in this paper. A dilated inception module for local feature extraction and a text self-attention module for non-local feature extraction are presented, and these two kinds of modules are integrated into single shot detector (SSD) of generic object detection so as to perform multi-oriented text detection in natural scene. The proposed modules make a contribution to richer and wider receptive field and enhance feature representation. Furthermore, the performance of our text detector is improved. In addition, compared with previous text detectors based on SSD which classify positive and negative samples depending on default boxes, we exploit pixels as reference for more accurate matching with ground truth which avoids complex anchor design. Furthermore, to evaluate the effectiveness of the proposed method, we carry out several comparative experiments on public standard benchmarks and analyze the experimental results in detail. The experimental results illustrate that the proposed text detector can compete with the state-of-the-art methods. |
关键词 | Text detection Natural scene text Convolutional neural network Attention mechanism |
DOI | 10.1007/s10032-020-00356-y |
收录类别 | SCI |
语种 | 英语 |
资助项目 | National Key R&D Program of China[2017YFB1401000] ; China Postdoctoral Science Foundation[2018M641524] ; Science and Technology Program of Beijing[Z201100001820002] |
项目资助者 | National Key R&D Program of China ; China Postdoctoral Science Foundation ; Science and Technology Program of Beijing |
WOS研究方向 | Computer Science |
WOS类目 | Computer Science, Artificial Intelligence |
WOS记录号 | WOS:000555756400001 |
出版者 | SPRINGER HEIDELBERG |
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 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/40375 |
专题 | 数字内容技术与服务研究中心_版权智能与文化计算 |
通讯作者 | Zheng, Yang |
作者单位 | 1.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 3.Beijing Film Acad, AICFVE, Beijing 100088, Peoples R China |
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 | Li, XiaoQian,Liu, Jie,Zhang, ShuWu,et al. Single shot multi-oriented text detection based on local and non-local features[J]. INTERNATIONAL JOURNAL ON DOCUMENT ANALYSIS AND RECOGNITION,2020(2020):241-252. |
APA | Li, XiaoQian,Liu, Jie,Zhang, ShuWu,Zhang, GuiXuan,&Zheng, Yang.(2020).Single shot multi-oriented text detection based on local and non-local features.INTERNATIONAL JOURNAL ON DOCUMENT ANALYSIS AND RECOGNITION(2020),241-252. |
MLA | Li, XiaoQian,et al."Single shot multi-oriented text detection based on local and non-local features".INTERNATIONAL JOURNAL ON DOCUMENT ANALYSIS AND RECOGNITION .2020(2020):241-252. |
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 | ||
SingleShotMultiorien(2525KB) | 期刊论文 | 出版稿 | 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