全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...
电子学报  2015 

基于视觉显著性与文字置信图的场景文字的背景抑制方法

DOI: 10.3969/j.issn.0372-2112.2015.01.010, PP. 62-68

Keywords: 场景文字,背景抑制,视觉显著性,笔画特征,傅里叶谱统计特征

Full-Text   Cite this paper   Add to My Lib

Abstract:

复杂背景是影响场景文字自动定位算法性能的重要因素.为消除背景干扰,本文首先根据谱残差理论获取显著性区域,然后利用基于笔画特征的点对梯度方向差比例图与基于傅里叶谱统计特征的后验概率图取得显著性区域的文字置信图,最后借助图模型融合视觉显著性图、文字置信图与HSI颜色特征最终达到抑制自然图像背景并突出前景文字的效果.在ICDAR2011场景文字定位竞赛数据库与实验室场景中文数据库中的实验结果表明,本算法可较好的抑制自然图像中复杂背景,并有效提升算法的性能.

References

[1]  冯松鹤,等.一种融合图学习与区域显著性分析的图像检索算法[J].电子学报,2011,39(10):2288-2294. Feng S h,et al.Combining graph learning and region saliency analysis for content based image retrieval [J].Acta Electronica Sinica,2011,39(10):2288-2294.(in Chinese)
[2]  钱晓亮,等.一种基于加权稀疏编码的频域视觉显著性检测算法[J].电子学报,2013,41(6):1159-1165. Qiao X L,et al.A spectral algorithm based on weighted sparse coding for visual saliency detection [J].Acta Electronica Sinica,2013,41(6):1159-1165.(in Chinese)
[3]  田破荒,等.基于文字穿越线和笔画连通性的视频文字提取方法[J].电子学报,2009,37(1):72-78. Tian P H,et al.An approach for video-text extraction based on text traversing line and stroke connectivity [J].Acta Electronica Sinica,2009,37(1):72-78.(in Chinese)
[4]  Bai B,Yin F,Liu C L.Scene text localization using gradient local correlation [A].International Conference on Document Analysis and Recognition [C].Washington DC:IEEE,2013.1412-1416.
[5]  Yao C,et al.Detecting texts of arbitrary orientations in natural images [A].IEEE Conference on Computer Vision and Pattern Recognition,Providence [C].USA:IEEE,2012.1083-1090.
[6]  姜维,卢朝阳,李静,等.基于角点类别特征和边缘幅值方向梯度直方图统计特征的复杂场景文字定位算法[J].吉林大学学报(工学版),2013,43(1):250-255. Jiang W,Lu Z Y,Li J,et al.Text localization algorithm in complex scene based on corner-type feature and histogram of oriented gradients of edge magnitude statistical feature [J].Journal of Jilin University Engineering and Technology Edition,2013,43(1):250-255.(in Chinese)
[7]  MengQ,Song Y H.Text detection in natural scenes with salient region [A].International Workshop on Document Analysis Systems [C].Gold Cost:IEEE,2012.384-388.
[8]  Sun Q Y,Yue L,Sun S L.Avisual attention based approach to text extraction [A].International Conference on Pattern Recognition [C].Istanbul:IEEE,2010.3991-3995.
[9]  Shi C Z,Xiao B H,Wang C H,et al.Graph-based background suppression for scene text detection [A].International IAPR Workshop on Document Analysis Systems [C].Queensland:IEEE,2012.210-214.
[10]  Hou X D and Zhang L Q.Saliency detection:a spectral residual approach [A].IEEE Conference on Computer Vision and Pattern Recognition [C].Minneapolis:IEEE,2007.1-8.
[11]  Honey C,Kirchner H,Van Rullen R.Faces in the cloud:Fourier power spectrum biases ultrarapid face detection [J].Journal of Vision,2008,8(12):1-13.
[12]  Epshtein B,Ofek E,Wexler Y.Detecting text in natural scenes with stroke width transform [A].IEEE Conference on Computer Vision and Pattern Recognition [C].San Francisco:IEEE,2010.2963-2970.
[13]  Zhang J,Kasturi R.Character energy and link energy-based text extraction in scene images [A].Asian Conference on Computer Vision,Queenstown [C].Berlin Heidelberg:Springer,2011.308--320.
[14]  Ruderman D.Thestatistics of natural images [J].Network:Computation in Neural Systems,1994,5(4):517-548.
[15]  Boykov Y,Jolly P.Interactive graph cuts for optimal boundary & region segmentation of objects in n-d images [A].IEEE International Conference on Computer Vision [C].Vancouver:IEEE,2001.105-112.
[16]  Boykov Y,Kolmogorov V.An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision [J].IEEE Transaction Pattern Analysis and Machine Intelligence,2004,26(9):1124-1137.
[17]  Shahab A,Shafait F,Dengel A.Howsalient is Scene text [A].International Workshop on Document Analysis Systems [C].Gold Cost:IEEE,2012.317-321.
[18]  Lyu M R,Song J Q,Cai M.A comprehensive method for multilingual video text detection,localization,and extraction [J].IEEE Transactions on Circuits and Systems for Video Technology,2005,15(2):243-255.
[19]  Liu C M,Wang C H,Dai R W.Text detection in images based on unsupervised classification of edge-based features [A].International Conference on Document Analysis and Recognition [C].Seoul:IEEE,2005.610-614.
[20]  Shahab A,Shafait F,Dengel A.Dengel ICDAR 2011 robust reading competition challenge 2:Reading text in scene images [A].International Conference on Document Analysis and Recognition [C].Beijing:IEEE,2011.1491-1496.

Full-Text

Contact Us

[email protected]

QQ:3279437679

WhatsApp +8615387084133