Seam Carving for Text Line Extraction on Color and Grayscale Historical Manuscripts

被引:52
作者
Arvanitopoulos, Nikolaos [1 ]
Suesstrunk, Sabine [1 ]
机构
[1] Ecole Polytech Fed Lausanne EPFL, Sch Comp & Commun Sci IC, Lausanne, Switzerland
来源
2014 14TH INTERNATIONAL CONFERENCE ON FRONTIERS IN HANDWRITING RECOGNITION (ICFHR) | 2014年
关键词
D O I
10.1109/ICFHR.2014.127
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We propose a novel algorithm for automatic text line extraction on color and grayscale manuscript pages without prior binarization. Our algorithm is based on seam carving to compute separating seams between text lines. Seam carving is likely to produce seams that move through gaps between neighboring lines, if no information about the text geometry is incorporated into the problem. By constraining the optimization procedure inside the region between two consecutive text lines, we can produce robust separating seams that do not cut through word and line components. Extensive experimental evaluations on diverse manuscript pages show that we improve upon the state-of-the-art for grayscale text line extraction.
引用
收藏
页码:726 / 731
页数:6
相关论文
共 22 条
[1]   Seam carving for content-aware image resizing [J].
Avidan, Shai ;
Shamir, Ariel .
ACM TRANSACTIONS ON GRAPHICS, 2007, 26 (03)
[2]   Text Line Extraction using DMLP Classifiers for Historical Manuscripts [J].
Baechler, Micheal ;
Liwicki, Marcus ;
Ingold, Rolf .
2013 12TH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION (ICDAR), 2013, :1029-1033
[3]  
Bukhari Syed Saqib, 2009, 2009 10th International Conference on Document Analysis and Recognition (ICDAR), P446, DOI 10.1109/ICDAR.2009.206
[4]   Text-Line Extraction using a Convolution of Isotropic Gaussian Filter with a Set of Line Filters [J].
Bukhari, Syed Saqib ;
Shafait, Faisal ;
Breuel, Thomas M. .
11TH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION (ICDAR 2011), 2011, :579-583
[5]  
Bulacu M, 2007, PROC INT CONF DOC, P357
[6]  
Fischer A., 2012, INT INTERDISCIPLINAR
[7]  
Fischer A., 2010, P 9 IAPR INT WORKSH, P3, DOI [10.1145/1815330.1815331, DOI 10.1145/1815330.1815331]
[8]   Automatic Transcription of Handwritten Medieval Documents [J].
Fischer, Andreas ;
Wuethrich, Markus ;
Liwicki, Marcus ;
Frinken, Volkmar ;
Bunke, Horst ;
Viehhauser, Gabriel ;
Stolz, Michael .
2009 15TH INTERNATIONAL CONFERENCE ON VIRTUAL SYSTEMS AND MULTIMEDIA PROCEEDINGS (VSMM 2009), 2009, :137-+
[9]  
Garz A., 2012, Proceedings of the 10th IAPR International Workshop on Document Analysis Systems (DAS 2012), P95, DOI 10.1109/DAS.2012.23
[10]   A Binarization-Free Clustering Approach to Segment Curved Text Lines in Historical Manuscripts [J].
Garz, Angelika ;
Fischer, Andreas ;
Bunke, Horst ;
Ingold, Rolf .
2013 12TH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION (ICDAR), 2013, :1290-1294