Text Line Segmentation With Water Flow Algorithm Based on Power Function

Darko Brodić 1
  • 1 University of Belgrade, Technical Faculty Bor, Vojske Jugoslavije 12, 19210 Bor, Serbia


This manuscript proposes an extension to the water flow algorithm for text line segmentation. Basic algorithm assumes hypothetical water flows under few specified angles of the document image frame from left to right and vice versa. As a result, unwetted image regions that incorporate text are extracted. These regions are of the major importance for text line segmentation. The extension of the basic algorithm means modification of water flow function that creates the unwetted region. Hence, the linear water flow function used in the basic algorithm is changed with its power function counterpart. Extended method was tested, examined and evaluated under different text samples. Results are encouraging due to improving text line segmentation which is a key process stage.

If the inline PDF is not rendering correctly, you can download the PDF file here.

  • [1] RAZAK, Z.-ZULKIFLEE, K.et al : Off-Line Handwriting Textline Segmentation: A Review, International Journal of Com- puter Science and Network Security 8 No. 7 (2008), 12-20.

  • [2] LIKFORMAN-SULEM, L.-ZAHOUR, A.-TACONET, B. : Text Line Segmentation of Historical Documents: A Survey, In- ternational Journal on Document Analysis and Recognition 9 No. 2-4 (2007), 123-138.

  • [3] YI, L.-YEFENG, Z.-DOERMANN, D.-JAEGER, S. : Script-Independent Text Line Segmentation in Freestyle Hand- written Documents, IEEE Transactions on Pattern Analysis and Machine Intelligence 30 No. 8 (2008), 1313-1329.

  • [4] PLAMONDON, R.-SRIHARI, S. N. : Online and Offline Handwriting Recognition:AComprehensive Survey,IEEE Trans- actions on Pattern Analysis and Machine Intelligence 22 No. 1 (2000), 63-84.

  • [5] ZRAMDINI, A.-INGLOD, R. : Optical Font Recognition from Projection Profiles, Electronic Publishing 6 No. 3 (1993), 249-260.

  • [6] SILVA, L. F.-CONCI, A.-SANCHEZ, A. : Automatic Dis- crimination between Printed and Handwritten Text in Docu- ments, In Proceedings of 22nd Brazilian Symposium on Com- puter Graphics and Image Processing, Rio de Janeiro (Brazil), 2009, pp. 261-267.

  • [7] BALLARD, D. H. : Generalizing the Hough Transforms to De- tect Arbitrary Shapes, Pattern Recognition 13 No. 2 (1981), 111-122.

  • [8] AMIN, A.-FISCHER, A. A. : Document Skew Detection Method using the Hough Transform, Pattern Analysis & Ap- plications 3 No. 3 (2000), 243-253.

  • [9] BALLARD, D. H.-BROWN, C. M. : Computer Vision, Pren- tice Hall, Englewood Cliffs, N.J., U.S.A., 1982, pp. 149-165.

  • [10] WAHL, F. M.-WONG, K. Y.-CASEY, R. G. : Block Segmen- tation and Text Extraction in Mixed Text/Image Documents,, Computer Graphics and Image Processing 20 No. 2 (1982), 375-390.

  • [11] SHI, Z.-GOVINDARAJU, V. : Line Separation for Complex Document Images using Fuzzy Runlength, In Proceedings of the International Workshop on Document Image Analysis for Libraries ’04, Palo Alto (U.S.A.), 2004, pp. 306-312.

  • [12] YIN, F.-LIU, C. : A Variational Bayes Method for Handwrit- ten Text Line Segmentation, In Proceedings of the 10th Interna- tional Conference on Document Analysis and Recognition (IC- DAR ’09), Barcelona (Spain), 2009, pp. 436-440.

  • [13] TRIPATHY, N.-PAL, U. Handwriting Segmentation of Un- constrained Oriya Text : Sadhana 31 No. 6 (2006), 755-769.

  • [14] DU, X.-PAN, W.-BUI, T. D. : Text Line Segmentation in Handwritten Documents using Mumford-Shah Model, Pattern Recognition 42 No. 12 (2009), 3136-3145.

  • [15] LIKFORMAN-SULEM, L.-FAURE, C. Extracting Lines on Handwritten Documents by Perceptual Grouping : In Advances in Handwriting and Drawing: a Multidisciplinary Approach (C. Faure, P. Keuss, G. Lorette, A. Winter, eds.), Paris: Europia, 1994, pp. 21-38.

  • [16] KHANDEWAL, A.-CHOUDHURY, P.-SARKAR, R.-BA- SU, S.-NASIPURI, M.-DAS, N. : Text Line Segmentation for Unconstrained Handwritten Document Images using Neighbor- hood Connected Component Analysis, Proceedings of the 3rd International Conference on Pattern Recognition and Machine Intelligence (PReMI ’09) (S. Chaudhury et al , eds.), LNCS 5909, pp. 369-374.

  • [17] ZAHOUR, A.-TACONET, B.-MERCY, P.-RAMDANE, S. : Arabic Handwritten Text-Line Extraction, In Proceedings of the 6th International Conference on Document Analysis and Recognition (ICDAR ’01), Seattle (U.S.A.), 2001, pp. 281-285.

  • [18] KOSHINAKA, T.-KEN’ICHI, I.-AKITOSHI, O. : An HMM- Based Text Segmentation Method using Variational Bayes Ap- proach, IEIC Technical Report 104 No. 87 (2004), 19-24.

  • [19] ABUHAIBA, I. S. I.-DATTA, S.-HOLT, M. J. J. : Line Extraction and Stroke Ordering of Text Pages, In Proceed- ings of the 3rd International Conference on Document Anal- ysis and Recognition (ICDAR ’95), Montreal (Canada), 1995, pp. 390-393.

  • [20] SESH KUMAR, K. S.-NAMBOODIRI, A. M.-JAWAHAR, C. V. : Learning Segmentation of Documents with Complex Scripts, In Proceedings of the 5th Indian Conference on Com- puter Vision, Graphics and Image Processing, LNCS 4338, Madurai (India), 2006, pp. 749-760.

  • [21] BASU, S.-CHAUDHURI, C.-KUNDU, M.-NASIPURI, M. -BASU, D. K. : Text Line Extraction from Multi-Skewed Handwritten Document, Pattern Recognition 40 No. 6 (2006), 1825-1839.

  • [22] BRODI´C, D.-MILIVOJEVI´C, Z. : A New Approach to Water Flow Algorithm for Text Line Segmentation, Journal of Univer- sal Computer Science 17 No. 1 (2011), 30-47.

  • [23] NIBLACK, W. : An Introduction to Digital Image Processing, Prentice Hall, Englewood Cliffs, N.J., U.S.A., 1986.

  • [24] SAUVOLA, L.-PIETIKAINEN, M. : Adaptive Document Im- age Binarization, Pattern Recognition 33 No. 2 (2000), 225-236.

  • [25] STATHIS, P.-KAVALLIERATOU, E.-PAPAMARKOS, N. : An Evaluation Technique for Binarization Algorithms, Journal of Universal Computer Science 14 No. 18 (2008), 3011-3030.

  • [26] KHASMAN, A.-SEKEROGLU, B. : Document Image Binari- sation using a Supervised Neural Network, International Journal of Neural Systems 18 No. 5 (2008), 405-418.

  • [27] PREPARATA, F. P.-SHAMOS, M. I. : Computational Ge- ometry: An Introduction, Springer, Berlin, 1995.

  • [28] WANG, J.-LEUNG, M. K. H.-HUI, S. C. : Cursive Word Reference Line Detection, Pattern Recognition 30 No. 3 (1997), 503-511.

  • [29] BRODI´C, D.-MILIVOJEVI´C, Z. : An Approach to Modifica- tion of Water Flow Algorithm for Segmentation and Text Pa- rameters Extraction, In Emerging Trends in Technological In- novation (L.M. Camarinha-Matos, P. Pereira, L. Ribeiro, eds.), Proceedings of First IFIP WG 5.5/SOCOLNET Doctoral Con- ference on Computing, Electrical and Industrial Systems (Do- CEIS ’2010), vol. 314, Costa de Caparica (Portugal) IFIP AICT, pp. 324-331, DOI: 10.1007/978-3-642-11628-5 35.

  • [30] BRODI´C, D.-MILIVOJEVI´C, Z. : Text Line Segmentation by Adapted Water Flow Algorithm, In Proceedings of 10th Sympo- sium on Neural Network Applications in Electrical Engineering (NEUREL ’2010), Belgrade (Serbia), 2010, pp. 225-229.

  • [31] BRODI´C, D.-MILIVOJEVI´C, D. R.-MILIVOJEVI´C, Z. : Basic Test Framework for the Evaluation of Text Line Segmen- tation and Text Parameter Extraction, Sensors 10 No. 5 (2010), 5263-5279.

  • [32] BRODI´C, D. : Basic Experiments Set for the Evaluation of the Text Line Segmentation, Przeglad Elektrotechniczny (Electrical Review) 86 No. 11 (2010,), 353-357.

  • [33] BRODI´C, D. : Advantages of the Extended Water Flow Algo- rithm for Handwritten Text Line Segmentation, In Proceedings of the 4th International Conference Pattern Recognition and Machine Intelligence (PReMI ’11), Moscow (Russia), 2011, (ac- cepted).

  • [34] BRODI´C, D.-DOKI´C, B. : Initial Skew Rate Detection us- ing Rectangular Hull Gravity Center, In 14th International Conference on Electronics - E’2010, Vilnius (Lithuania), 2010 Sect.3.24, pp. 1-6.

  • [35] SANCHEZ, A.-SUAREZ, P. D.-MELLO, C. A. B.-OLIVEI- RA, A. L. I.-ALVES, V. M. O. : Text Line Segmentation in Images of Handwritten Historical Documents, In Proceedings of First International Workshops on Image Processing Theory, Tools and Applications, Sousse (Tunisia), 2008, pp. 1-6.

  • [36] MING, M.-PENG, Y.-SPRING. M. : Ontology Mapping: As a Binary Classification Problem, In Proceedings of the 4th Inter- national Conference on Semantics, Knowledge and Grid, Beijing (China), 2008.

  • [37] SWETS, J. A. : Measuring the Accuracy of Diagnostic Systems, Science (New Series) 240 No. 4857 (1988), 1285-1293.

  • [38] FAWCETT, T. : ROC Graphs: Notes and Practical Consider- ations for Data Mining Researchers, HP Invent (2003), 1-27.

  • [39] ABDI, H. : Signal Detection Theory, In Encyclopedia of Mea- surement and Statistics (Salkind, ed.), 2007, pp. 1-9.

  • [40] QIAN, X.-LIU, G.-WANG, H.-SU, R. : Text Detection, Lo- calization, and Tracking in Compressed Video, Signal Process- ing: Image Communication 22 No. 9 (2007), 752-768.

  • [41] BUKHARI, S. S.-SHAFAIT, F.-BRUESL, T. M. : Adaptive Binarization of Unconstrained Hand-Held Camera-Captured Document Images, Journal of Universal Computer Science 15 No. 18 (2009), 3343-3363.

  • [42] BRODI´C, D.-MILIVOJEVI´C, Z. : A New Approach to Water Flow Algorithm for Text Line Segmentation, Journal of Univer- sal Computer Science 17 No. 1 (2011), 30-47.

  • [43] BRODI´C, D.-MILIVOJEVI´C, D. R.-MILIVOJEVI´C, Z. : An Approach to a Comprehensive Test Framework for Analysis and Evaluation of Text Line Segmentation Algorithms, Sensors 11 No. 9 (2011), 8782-8812.


Journal + Issues