CASIA OpenIR  > 数字内容技术与服务研究中心  > 听觉模型与认知计算
Detecting Uyghur text in complex background images with convolutional neural network
Fang, Shancheng1,2; Xie, Hongtao1,2; Chen, Zhineng3; Zhu, Shiai4; Gu, Xiaoyan1,2; Gao, Xingyu5
AbstractUyghur text detection is crucial to a variety of real-world applications, while little researches put their attention on it. In this paper, we develop an effective and efficient region-based convolutional neural network for Uyghur text detection in complex background images. The characteristics of the network include: (1) Three region proposal networks are used to improve the recall, which simultaneously utilize feature maps from different convolutional layers. (2) The overall architecture of our network is in the form of fully convolutional network, and global average pooling is applied to replace the fully connected layers in the classification and bounding box regression layers. (3) To fully utilize the baseline information, Uyghur text lines are detected directly by the network in an end-to-end fashion. Experiment results on benchmark dataset show that our method achieves an F-measure of 0.83 and detection time of 0.6 s for each image in a single K20c GPU, which is much faster than the state-of-the-art methods while keeps competitive accuracy.
KeywordUyghur Text Detection Text Localization Convolutional Neural Network
WOS HeadingsScience & Technology ; Technology
Indexed BySCI
Funding OrganizationNational Nature Science Foundation of China(61303171 ; "trategic Priority Research Program" of the Chinese Academy of Sciences(XDA06031000) ; 61303175)
WOS Research AreaComputer Science ; Engineering
WOS SubjectComputer Science, Information Systems ; Computer Science, Software Engineering ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS IDWOS:000403039400030
Citation statistics
Document Type期刊论文
Affiliation1.Chinese Acad Sci, Inst Informat Engn, Natl Engn Lab Informat Secur Technol, Beijing, Peoples R China
2.Univ Chinese Acad Sci, Sch Cyber Secur, Beijing, Peoples R China
3.Chinese Acad Sci, Inst Automat, Interact Digital Media Technol Res Ctr, Beijing, Peoples R China
4.Univ Ottawa, Ottawa, ON, Canada
5.Chinese Acad Sci, Inst Software, Lab Parallel Software & Computat Sci, Beijing, Peoples R China
Recommended Citation
GB/T 7714
Fang, Shancheng,Xie, Hongtao,Chen, Zhineng,et al. Detecting Uyghur text in complex background images with convolutional neural network[J]. MULTIMEDIA TOOLS AND APPLICATIONS,2017,76(13):15083-15103.
APA Fang, Shancheng,Xie, Hongtao,Chen, Zhineng,Zhu, Shiai,Gu, Xiaoyan,&Gao, Xingyu.(2017).Detecting Uyghur text in complex background images with convolutional neural network.MULTIMEDIA TOOLS AND APPLICATIONS,76(13),15083-15103.
MLA Fang, Shancheng,et al."Detecting Uyghur text in complex background images with convolutional neural network".MULTIMEDIA TOOLS AND APPLICATIONS 76.13(2017):15083-15103.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Fang, Shancheng]'s Articles
[Xie, Hongtao]'s Articles
[Chen, Zhineng]'s Articles
Baidu academic
Similar articles in Baidu academic
[Fang, Shancheng]'s Articles
[Xie, Hongtao]'s Articles
[Chen, Zhineng]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Fang, Shancheng]'s Articles
[Xie, Hongtao]'s Articles
[Chen, Zhineng]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.