›› 2012, Vol. 27 ›› Issue (1): 187-194.doi: 10.1007/s11390-012-1216-1

• Graphics, Visualization, and Image Processing • Previous Articles     Next Articles

Extended Approach to Water Flow Algorithm for Text Line Segmentation

Darko Brodi?, Student Member, IEEE   

  1. Technical Faculty in Bor, University of Belgrade, Vojske Jugoslavije 12, 19210 Bor, Serbia
  • Received:2011-05-13 Revised:2011-11-12 Online:2012-01-05 Published:2012-01-05

This paper proposes a new approach to the water flow algorithm for text line segmentation. In the basic method the hypothetical water flows under few specified angles which have been defined by water flow angle as parameter. It is applied to the document image frame from left to right and vice versa. As a result, the unwetted and wetted areas are established. These areas separate text from non-text elements in each text line, respectively. Hence, they represent the control areas that are of major importance for text line segmentation. Primarily, an extended approach means extraction of the connected-components by bounding boxes over text. By this way, each connected component is mutually separated. Hence, the water flow angle, which defines the unwetted areas, is determined adaptively. By choosing appropriate water flow angle, the unwetted areas are lengthening which leads to the better text line segmentation. Results of this approach are encouraging due to the text line segmentation improvement which is the most challenging step in document image processing.

[1] Likforman-Sulem L, Zahour A, Taconet B. Text line seg-mentation of historical documents: A survey. InternationalJournal on Document Analysis and Recognition, 2007, 9(2-4):123-138.

[2] Amin A,Wu S. Robust skew detection in mixed text/graphicsdocuments. In Proc. of the 8th ICDAR, Seoul, Korea,Aug. 29-Sept. 1, 2005, pp.247-251.

[3] Razak Z, Zulkiflee K et al. Off-line handwriting text linesegmentation: A review. International Journal of ComputerScience and Network Security (IJCSNS), 2008, 8(7): 12-20.

[4] Shi Z, Govindaraju V. Line separation for complex documentimages using fuzzy runlength. In Proc. the 1st Int. Work-shop on Document Image Analysis for Libraries, Palo Alto,USA, Jan. 24, 2004, pp.306-312.

[5] Yi L, Zhong Y, Doermann D, Jaeger S. Script-independenttext line segmentation in freestyle handwritten documents.IEEE Transactions on Pattern Analysis and Machine Intel-ligence, 2008, 30(8): 1313-1329.

[6] Basu S, Chaudhuri C, Kundu M, Nasipuri M, Basu D K. Textline extraction from multi-skewed handwritten documents.Pattern Recognition, 2007, 40(6): 1825-1839.

[7] Brodi? D, Milivojevi? Z. An Approach to modification ofwater flow algorithm for segmentation and text parametersextraction. In IFIP Advances in Information and Commu-nication Technology 314, Camarinha-Matos L M, Pereira P,Ribeiro L (eds.), Springer-Verlag, 2010, pp.324-331.

[8] Brodi? D, Milivojevi? Z. A new approach to water flow algo-rithm for text line segmentation. Journal of Universal Com-puter Science, 2011, 17(1): 30-47.

[9] Gonzalez R C, Woods R E. Digital Image Processing, 3rdedition. Prentice-Hall, 2007.

[10] Otsu N. A threshold selection method from gray-level his-tograms. IEEE Transactions on Systems, Man, and Cyber-netics, 1979, 9(1): 62-66.

[11] TsaiWH. Moment-preserving thresholding: A new approach.Computer Vision, Graphics, and Image Processing, 1985,29(3): 377-393.

[12] Sanchez A, Suarez P D, Mello C A B, Oliveira A L I, AlvesV M O. Text line segmentation in images of handwritten his-torical documents. In Proc. the 1st IPTA, Sousse, Tunisia,2008, pp.1-6.

[13] Preparata F P, Shamos M I. Computational Geometry: AnIntroduction. Springer, 1985.

[14] Wang J, Leung M K H, Hui S C. Cursive word reference linedetection. Pattern Recognition, 1997, 30(3): 503-511.

[15] Brodi? D, Milivojevi? D R, Milivojevi? Z. Basic test frame-work for the evaluation of text line segmentation and textparameter extraction. Sensors, 2010, 10(5): 5263-5279.

[16] Brodi? D. Methodology for the evaluation of the algorithmsfor text line segmentation based on extended binary classifi-cation. Measurement Science Review, 2011, 11(3): 71-78.

[17] Brodi? D. Advantages of the extended water flow algorithmfor handwritten text segmentation. In Lecture Notes in Com-puter Science 6744, Kuznetsov S O et al. (eds.), Springer-Verlag, 2011, pp. 418-423.

[18] Brodi? D, Milivojevi? D R, Milivojevi? Z. An approach toa comprehensive test framework for analysis and evaluationof text line segmentation algorithms. Sensors, 2011, 11(9):8782-8812.

[19] Swets J A. Measuring the accuracy of diagnostic systems. Sci-ence, 1988, 240(4857): 1285-1293.

[20] Qian X, Liu G, Wang H, Su R. Text detection, localization,and tracking in compressed video. Signal Processing: ImageCommunication, 2007, 22(9): 752-768.

[21] Brodi? D. The evaluation of the initial skew rate for printedtext. Journal of Electrical Engineering | Elektrotechnick?y·casopis, 2011, 62(3): 134-140.
No related articles found!
Full text



[1] Wu Xindong;. Inductive Learning[J]. , 1993, 8(2): 22 -36 .
[2] Ma Jun; Ma Shaohan;. Efficient Parallel Algorithms for Some Graph Theory Problems[J]. , 1993, 8(4): 76 -80 .
[3] Jin Guohua; Chen Fujie;. On the Problem of Optimizing Parallel Programs for Complex Memory Hierarchies[J]. , 1994, 9(1): 1 -26 .
[4] Zhou Jianqiang; Xie Li; Dai Fei; Sun Zhongxiu;. Adaptive Memory Coherence Algorithms in DSVM[J]. , 1994, 9(4): 365 -372 .
[5] Zhang Songmao;. Weak Precedence Story Parsing Grammar[J]. , 1995, 10(1): 53 -64 .
[6] Yu Shengke;. Reasoning in H-Net: A Unified Approach to Intelligent Hypermedia Systems[J]. , 1996, 11(1): 83 -89 .
[7] Peng Chenglian;. Combining Gprof and Event-Driven Monitoring for Analyzing Distributed Programs:A Rough View of NCSA Mosaic[J]. , 1996, 11(4): 427 -432 .
[8] Tao Xuehong; Sun Wei; Ma Shaohan;. A Practical Propositional Knowledge Base Revision Algorithm[J]. , 1997, 12(2): 154 -159 .
[9] Li Bin; Liang Xundong; Liu Shenquan;. A Surface Rendering Approach in 3D Rectilinear Datafield[J]. , 1998, 13(3): 220 -227 .
[10] NIE Xumin; GUO Qing;. Renaming a Set of Non-Horn Clauses[J]. , 2000, 15(5): 409 -415 .

ISSN 1000-9000(Print)

CN 11-2296/TP

Editorial Board
Author Guidelines
Journal of Computer Science and Technology
Institute of Computing Technology, Chinese Academy of Sciences
P.O. Box 2704, Beijing 100190 P.R. China
E-mail: jcst@ict.ac.cn
  Copyright ©2015 JCST, All Rights Reserved