Integrated Method for Text Detection in Natural Scene Images
Yang Zheng1; Jie Liu2; Heping Liu1; Qing Li1; Gen Li2
Source PublicationKSII TRANSACTIONS ON INTERNET AND INFORMATION SYSTEMS
2016-11-30
Volume10Issue:11Pages:5583-5604
AbstractIn this paper, we present a novel image operator to extract textual information in natural scene images. First, a powerful refiner called the Stroke Color Extension, which extends the widely used Stroke Width Transform by incorporating color information of strokes, is proposed to achieve significantly enhanced performance on intra-character connection and non-character removal. Second, a character classifier is trained by using gradient features. The classifier not only eliminates non-character components but also remains a large number of characters. Third, an effective extractor called the Character Color Transform combines color information of characters and geometry features. It is used to extract potential characters which are not correctly extracted in previous steps. Fourth, a Convolutional Neural Network model is used to verify text candidates, improving the performance of text detection. The proposed technique is tested on two public datasets, i.e., ICDAR2011 dataset and ICDAR2013 dataset. The experimental results show that our approach achieves state-of-the-art performance.; In this paper, we present a novel image operator to extract textual information in natural scene images. First, a powerful refiner called the Stroke Color Extension, which extends the widely used Stroke Width Transform by incorporating color information of strokes, is proposed to achieve significantly enhanced performance on intra-character connection and non-character removal. Second, a character classifier is trained by using gradient features. The classifier not only eliminates non-character components but also remains a large number of characters. Third, an effective extractor called the Character Color Transform combines color information of characters and geometry features. It is used to extract potential characters which are not correctly extracted in previous steps. Fourth, a Convolutional Neural Network model is used to verify text candidates, improving the performance of text detection. The proposed technique is tested on two public datasets, i.e., ICDAR2011 dataset and ICDAR2013 dataset. The experimental results show that our approach achieves state-of-the-art performance.
KeywordStroke Color Extension Character Classifier Character Color Transform Convolutional Neural Network
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/19529
Collection数字内容技术与服务研究中心_新媒体服务与管理技术
Affiliation1.北京科技大学
2.中国科学院自动化研究所
Recommended Citation
GB/T 7714
Yang Zheng,Jie Liu,Heping Liu,et al. Integrated Method for Text Detection in Natural Scene Images[J]. KSII TRANSACTIONS ON INTERNET AND INFORMATION SYSTEMS,2016,10(11):5583-5604.
APA Yang Zheng,Jie Liu,Heping Liu,Qing Li,&Gen Li.(2016).Integrated Method for Text Detection in Natural Scene Images.KSII TRANSACTIONS ON INTERNET AND INFORMATION SYSTEMS,10(11),5583-5604.
MLA Yang Zheng,et al."Integrated Method for Text Detection in Natural Scene Images".KSII TRANSACTIONS ON INTERNET AND INFORMATION SYSTEMS 10.11(2016):5583-5604.
Files in This Item: Download All
File Name/Size DocType Version Access License
Integrated Method fo(880KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Yang Zheng]'s Articles
[Jie Liu]'s Articles
[Heping Liu]'s Articles
Baidu academic
Similar articles in Baidu academic
[Yang Zheng]'s Articles
[Jie Liu]'s Articles
[Heping Liu]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Yang Zheng]'s Articles
[Jie Liu]'s Articles
[Heping Liu]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Integrated Method for Text Detection in Natural Scene Images的副本.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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