基于自适应色彩聚类和上下文信息的自然场景文本检测

doi:10.3969/j.issn.0372-2112.2018.06.024

电子学报 ›› 2018, Vol. 46 ›› Issue (6): 1436-1444.DOI: 10.3969/j.issn.0372-2112.2018.06.024

基于自适应色彩聚类和上下文信息的自然场景文本检测

邹北骥^1,2, 郭建京^1,2, 朱承璋^1,2, 杨文君^1,2, 徐子雯^1,2

1. 中南大学信息科学与工程学院, 湖南长沙 410083;
2. 中南大学眼科医学影像处理研究中心, 湖南长沙 410083

收稿日期:2016-12-22 修回日期:2017-02-24 出版日期:2018-06-25
- 通讯作者:
- 朱承璋
- 作者简介:
- 邹北骥,男,1961年生于湖南邵阳.中南大学教授,博士生导师,研究方向为图像处理与计算机视觉.;郭建京,男,1990年生于湖南祁阳.硕士研究生,研究方向为计算机视觉与模式识别
- 基金资助:
- 国家自然科学基金 (No.61573380，No.61702559）; 湖南省科技计划项目 (No.2017WK2074）; 中南大学创新创业师生共创项目 (No.2017gczd016）

Natural Scene Text Detection Based on Adaptive Color Clustering and Context Information

ZOU Bei-ji^1,2, GUO Jian-jing^1,2, ZHU Cheng-zhang^1,2, YANG Wen-jun^1,2, XU Zi-wen^1,2

1. School of Information Science and Engineering, Central South University, Changsha, Hunan 410083, China;
2. Center for Ophthalmic Imaging Research, Central South University, Changsha, Hunan 410083, China

Received:2016-12-22 Revised:2017-02-24 Online:2018-06-25 Published:2018-06-25
- Corresponding author:
- ZHU Cheng-zhang
- Supported by:
- National Natural Science Foundation of China (No.61573380, No.61702559); Science and Technology Project of Hunan Province (No.2017WK2074); The Project for Innovation and Entrepreneurship of Teachers and Students of Central South University (No.2017gczd016)

摘要/Abstract

摘要： 自然场景文本检测是图像内容分析和理解的重要前提.本文提出一种基于自适应色彩聚类和上下文信息分析的方法，用于检测自然场景图像文本.首先，将层次聚类和参数自学习策略结合，设计一种自适应色彩聚类方法，提取图像中的候选字符.该自适应色彩聚类方法能针对不同图像自动学习权重阈值，有较好的字符召回率.然后，利用文本中字符成行出现的性质，设计一种基于上下文信息的字符验证策略，既能保证较高字符召回率，也能有效移除非文本字符.最后，合并字符构建文本行，并通过后处理得到文本检测结果.在ICDAR2013公共数据集上的实验结果表明：本文分别获得74.17%的召回率，83.40%的准确率和78.52%的F得分.与其他文本检测方法相比，本文获得了较好的文本检测性能，说明本文方法的优越性.

关键词: 自然场景文本检测, 自适应色彩聚类, 上下文信息, 自学习策略

Abstract: Natural scene text detection is an important task for image analysis and understanding.In this paper,a natural scene text detection method is proposed,using adaptive color clustering and context information analysis.Firstly,combining hierarchical clustering with self-learning strategy,we design an adaptive color clustering method,which learns clustering weights automatically and generates high character recall.Then,considering text in images usually containing several characters,we propose a character verification strategy based on image context information,which can guarantee high character recall and remove non-text components at the same time.Finally,characters are merged to text lines,and further post-processing is applied to generate final text detection results.Experiments on the ICDAR2013 publicly available dataset show that we obtain recall of 74.17%,precision of 83.40% and F-score of 78.52%.Compared with other text detection methods,our method obtains better text detection performance,indicating superiority of the proposed method.

Key words: natural scene text detection, adaptive color clustering, context information, self-learning strategy

中图分类号:

TP391.4

邹北骥, 郭建京, 朱承璋, 等. 基于自适应色彩聚类和上下文信息的自然场景文本检测[J]. 电子学报, 2018, 46(6): 1436-1444.

ZOU Bei-ji, GUO Jian-jing, ZHU Cheng-zhang, et al. Natural Scene Text Detection Based on Adaptive Color Clustering and Context Information[J]. Acta Electronica Sinica, 2018, 46(6): 1436-1444.

参考文献

[1] Wei B,Yin Z,Jie Y,et al.A novel approach to text detection and extraction from videos by discriminative features and density[J].Chinese Journal of Electronics,2014,23(2):322-328.
[2] Bai X,Yao C,Liu W.Strokelets:A learned multi-scale mid-level representation for scene text recognition[J].IEEE Transactions on Image Processing,2016,25(6):2789-2802.
[3] Wang X,Zha T,Wu C,et al.Text semantics based automatic summarization for chinese videos[J].Chinese Journal of Electronics,2015,24(3):462-467.
[4] 袁海东,马华东,黄晓冬.基于梯度与粗糙度的视频文本检测与定位[J].电子学报,2008,36(8):1660-1664. H.Yuan,H.Ma abd X.Huang.Video text detection and localization based on gradients and coarsenss[J].Acta Electronica Sinica,2008,36(8):1660-1665.(in Chinese)
[5] Lee J J,Lee P H,Lee S W,et al.AdaBoost for text detection in natural scene[A].2011 International Conference on Document Analysis and Recognition[C].Beijing,China:IEEE,2011.429-434.
[6] Wang T,Wu D J,Coates A,et al.End-to-end text recognition with convolutional neural networks[A].Proceedings of the 21st International Conference on Pattern Recognition[C].Tsukuba,Japan:IEEE,2012.3304-3308.
[7] Zhang Z,Wei S,Yao C,et al.Symmetry-based text line detection in natural scenes[A].2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)[C].Boston,USA:IEEE,2015.2558-2567.
[8] Neumann L,Matas J.Real-time scene text localization and recognition[A].2012 IEEE Conference on Computer Vision and Pattern Recognition[C].Providence,USA:IEEE,2012.3538-3545.
[9] Yin X C,Yin X,Huang K,et al.Robust text detection in natural scene images[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2014,36(5):970-983.
[10] Wang Q,Lu Y,Sun S.Text detection in nature scene images using two-stage nontext filtering[A].201513th International Conference on Document Analysis and Recognition (ICDAR)[C].Nancy,France:IEEE,2015.106-110.
[11] Yao C,Bai X,Liu W.A unified framework for multioriented text detection and recognition[J].IEEE Transactions on Image Processing A Publication of the IEEE Signal Processing Society,2014,23(11):4737-4749.
[12] Huang W,Lin Z,Yang J,et al.Text localization in natural images using stroke feature transform and text covariance descriptors[A].2013 IEEE International Conference on Computer Vision[C].Sydney,Australia:IEEE,2013.1241-1248.
[13] Epshtein B,Ofek E,Wexler Y.Detecting text in natural scenes with stroke width transform[A].2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition[C].San Francisco,USA:IEEE,2010.2963-2970.
[14] Wu H,Zou B,Zhao Y-Q,et al.Natural scene text detection by multi-scale adaptive color clustering and non-text filtering[J].Neurocomputing,2016,214:1011-1025.
[15] Wu H,Zou B,Zhao Y-Q,et al.Scene text detection using adaptive color reduction,adjacent character model and hybrid verification strategy[J].The Visual Computer,33(1):1-14.
[16] Yi C,Tian Y.Text string detection from natural scenes by structure-based partition and grouping[J].IEEE Transactions on Image Processing,2011,20(9):2594-2605.
[17] Yang Q,Tang J,Ahuja N.Efficient and robust specular highlight removal[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,37(6):1304-1311.
[18] Dalal N,Triggs B.Histograms of oriented gradients for human detection[A].2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)[C].San Diego,USA:IEEE,2005.886-893.
[19] Karatzas D,Shafait F,Uchida S,et al.ICDAR 2013 Robust Reading Competition[A].201312th International Conference on Document Analysis and Recognition[C].Washington DC,USA:IEEE,2013.1484-1493.
[20] Du Y,Duan G,Ai H.Context-based text detection in natural scenes[A].IEEE International Conference on Image Processing[C].Orlando,USA:IEEE,2012.1857-1860.
[21] Yin X C,Pei W Y,Zhang J,et al.Multi-orientation scene text detection with adaptive clustering[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,37(9):1930-1937.
[22] Shi C Z,Wang C H,Xiao B H,et al.Scene text recognition using structure-guided character detection and linguistic knowledge[J].IEEE Transactions on Circuits and Systems for Video Technology,2014,24(7):1235-1250.
[23] Yao C,Bai X,Liu W,et al.Detecting texts of arbitrary orientations in natural images[A].2012 IEEE Conference on Computer Vision and Pattern Recognition[C].Providence,USA:IEEE,2012.1083-1090.

基于自适应色彩聚类和上下文信息的自然场景文本检测

Natural Scene Text Detection Based on Adaptive Color Clustering and Context Information

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 4

编辑推荐

Metrics

[1]	王瑞豪, 刘哲, 宋余庆. 结合切片上下文信息的多阶段胰腺定位与分割[J]. 电子学报, 2021, 49(4): 706-715.
[2]	吕品, 李全刚, 柳厅文, 宁振虎, 王玉斌, 时金桥, 方滨兴. 基于双向LSTM的误植域名滥用检测方法[J]. 电子学报, 2018, 46(9): 2081-2086.
[3]	王凯丽, 张艳红, 肖斌, 李伟生. 一种基于二维局部二值模式的纹理图像分类方法[J]. 电子学报, 2018, 46(10): 2519-2526.
[4]	唐奇伶;龚红燕;李艳西;桑农. 融合上下文信息的血管造影图像增强[J]. 电子学报, 2008, 36(7): 1456-1459.