用户名: 密码: 验证码:
结合背景估计与能量函数的图像二值化算法
详细信息    查看全文 | 推荐本文 |
  • 英文篇名:Image binarization algorithm based on background estimation and energy function
  • 作者:熊炜 ; 王鑫睿 ; 王娟 ; 刘敏 ; 曾春艳
  • 英文作者:XIONG Wei;WANG Xin-rui;WANG Juan;LIU Min;ZENG Chun-yan;School of Electrical and Electronic Engineering,Hubei University of Technology;Hubei Collaborative Innovation Center for High-Efficiency Utilization of Solar Energy,Hubei University of Technology;
  • 关键词:文档图像二值化 ; 相对暗特征 ; 笔画宽度变换 ; 能量函数 ; 图割
  • 英文关键词:document image binarization;;relative darkness features;;stroke width transform;;energy function;;graph cut
  • 中文刊名:SJSJ
  • 英文刊名:Computer Engineering and Design
  • 机构:湖北工业大学电气与电子工程学院;湖北工业大学太阳能高效利用湖北省协同创新中心;
  • 出版日期:2019-07-16
  • 出版单位:计算机工程与设计
  • 年:2019
  • 期:v.40;No.391
  • 基金:国家自然科学基金项目(61501178、61571182、61601177);; 湖北省教育厅科学技术研究基金项目(D20161404);; 太阳能高效利用湖北省协同创新中心开放基金项目(HBSKFZD2014011)
  • 语种:中文;
  • 页:SJSJ201907030
  • 页数:7
  • CN:07
  • ISSN:11-1775/TP
  • 分类号:192-197+266
摘要
文档图像存在墨迹浸润等复杂背景特性,针对该问题,提出结合背景估计与能量函数的低质量文档图像二值化算法。基于相对暗特征和笔画宽度变换方法,估计文档图像的笔画宽度,采用形态学闭操作估计图像背景,通过能量函数最小化完成文档图像二值化。实验结果表明,该算法能有效抑制文档图像背景,取得较优的二值化结果,在F值(Fmeasure,FM)、伪F值(pseudo F-measure,p-FM)和错误率度量(negative rate metric,NRM)等性能指标上均优于LMM等经典二值化算法。
        Complex background features such as bleed through exist in document images,a degraded document image binarization algorithm based on background estimation and energy function was proposed.Combined relative darkness features with stroke width transform,the document background was estimated by morphological closing operations,and the document image binarization was completed by minimizing the energy function.Experimental results show that the proposed algorithm can effectively suppress the document background and obtain better binary results.The proposed method outperforms other state-of-the-art techniques in terms of F-measure,pseudo F-measure,and NRM.
引文
[1]Milyaev S,Barinova O,Novikova T,et al.Fast and accurate scene text understanding with image binarization and off-theshelf ocr[J].International Journal on Document Analysis and Recognition,2015,18(2):169-182.
    [2]Eskenazi S,Gomez-Krmer P,Ogier J-M.A comprehensive survey of mostly textual document segmentation algorithms since 2008[J].Pattern Recognition,2017,64(1):1-14.
    [3]Otsu N.A threshold selection method from gray-level histograms[J].IEEE Transactions on Systems,Man,and Cybernetics Systems,1979,9(1):62-66.
    [4]Wolf C,Jolion JM,Chassaing F.Text localization,enhancement and binarization in multimedia documents[C]//Proceedings of the 16th International Conference on Pattern Recognition.IEEE,2002:1037-1040.
    [5]Niblack W.An introduction to digital image processing[M].Englewood Cliffs:Prentice-Hall,1986:115-126.
    [6]Sauvola J,Pietikinen M.Adaptive document image binarization[J].Pattern recognition,2000,33(2):225-236.
    [7]Su B,Lu S,Tan CL.Binarization of historical document images using the local maximum and minimum[C]//Proceedings of the 9th IAPR International Workshop on Document Analysis Systems.ACM,2010:159-166.
    [8]Lu S,Su B,Tan CL.Document image binarization using background estimation and stroke edges[J].International Journal on Document Analysis and Recognition,2010,13(4):303-314.
    [9]Howe NR.A laplacian energy for document binarization[C]//Proceedings of the 11th International Conference on Document Analysis and Recognition.IEEE,2011:6-10.
    [10]Kligler N,Katz S,Tal A.Document enhancement using visibility detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2018:2374-2382.
    [11]Mustafa WA,Yazid H,Jaafar M.An improved sauvola approach on document images binarization[J].Journal of Telecommunication,Electronic and Computer Engineering,2018,10(2):43-50.
    [12]Bataineh B,Abdullah SNHS,Omar K.Adaptive binarization method for degraded document images based on surface contrast variation[J].Pattern Analysis and Applications,2017,20(3):639-652.
    [13]Jana P,Ghosh S,Bera SK,et al.Handwritten document image binarization:An adaptive K-means based approach[C]//Proceedings of the IEEE Conference on Calcutta Conference.IEEE,2017:226-230.
    [14]Ahmadi E,Azimifar Z,Shams M,et al.Document image binarization using a discriminative structural classifier[J].Pattern Recognition Letters,2015,63(1):36-42.
    [15]LIANG Tiancai,LIU Jianping,LUO Panfeng.A modified laplacian energy for document binarization[J].Computer Simulation,2015,32(9):276-280(in Chinese).[梁添才,刘建平,罗攀峰.一种改进拉普拉斯能量的文档图像二值化方法[J].计算机仿真,2015,32(9):276-280.]
    [16]Westphal F,Grahn H,Lavesson N.Efficient document image binarization using heterogeneous computing and parameter tuning[J].International Journal on Document Analysis and Recognition,2018,21(1-2):41-58.
    [17]Lu D,Huang X,Sui L.Binarization of degraded document images based on contrast enhancement[J].International Journal on Document Analysis and Recognition,2018,21(1-2):123-135.
    [18]Jia F,Shi C,He K,et al.Degraded document image binarization using structural symmetry of strokes[J].Pattern Recognition,2018,74(1):225-240.
    [19]Yin XC,Pei WY,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.
    [20]Panetta K,Gao C,Agaian S,et al.A new reference-based edge map quality measure[J].IEEE Transactions on Systems,Man,and Cybernetics Systems,2016,46(11):1505-1517.
    [21]Wu Y,Natarajan P,Rawls S,et al.Learning document image binarization from data[C]//Proceedings of the IEEEConference on Image Processing,2016:3763-3767.
    [22]Howe NR.Document binarization with automatic parameter tuning[J].International Journal on Document Analysis and Recognition,2013,16(3):247-258.
    [23]Pratikakis I,Gatos B,Ntirogiannis K.ICFHR 2012competition on handwritten document image binarization(H-DIBCO2012)[C]//Proceedings of the 13th International Conference on Frontiers in Handwriting Recognition.IEEE,2012:817-822.
    [24]Pratikakis I,Gatos B,Ntirogiannis K.ICDAR 2013document image binarization contest(DIBCO 2013)[C]//Proceedings of the 12th International Conference on Document Analysis and Recognition.IEEE,2013:1471-1476.
    [25]Ntirogiannis K,Gatos B,Pratikakis I.ICFHR2014competition on handwritten document image binarization(H-DIBCO2014)[C]//Proceedings of the 14th International Conference on Frontiers in Handwriting Recognition.IEEE,2014:809-813.
    [26]Pratikakis I,Zagoris K,Barlas G,et al.ICFHR2016handwritten document image binarization contest(H-DIBCO 2016)[C]//Proceedings of the 15th International Conference on Frontiers in Handwriting Recognition.IEEE,2016:619-623.
    [27]Pratikakis I,Zagoris K,Barlas G,et al.ICDAR2017competition on document image binarization(DIBCO 2017)[C]//Proceedings of the 14th IAPR International Conference on Document Analysis and Recognition.IEEE,2017:1395-1403.

© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号

地址:北京市海淀区学院路29号 邮编:100083

电话:办公室:(+86 10)66554848;文献借阅、咨询服务、科技查新:66554700