Text Line Segmentation with the Algorithm Based on the Oriented Anisotropic Gaussian Kernel

Darko Brodić 1  and Zoran N. Milivojević 2
  • 1 University of Belgrade, Technical Faculty Bor, V.J. 12, 19210 Bor, Serbia
  • 2 Technical College Niš, Aleksandra Medvedeva 20, 18000 Niš, Serbia

The paper presents the algorithm for text line segmentation based on the oriented anisotropic Gaussian kernel. Initially, the document image is split into connected components achieved by bounding boxes. These connected components are cleared from redundant fragments. Furthermore, the binary moments are applied to each of these connected components evaluating local text skewing. According to this information the orientation of the anisotropic Gaussian kernel is set. After the algorithm application the boundary growing areas around connected components are established. These areas are of major importance for the evaluation of text line segmentation. For testing purposes, the algorithm is evaluated under different text samples. Comparative analysis between algorithm with and without orientation based on the anisotropic Gaussian kernel is made. The results show the improvement in the domain of text line segmentation.

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

  • [1] LIKFORMAN SULEM, L.-ZAHOUR, A.-TACONET, B. : Text Line Segmentation of Historical Documents: a Survey, International Journal on Document Analysis and Recognition 9 No. 2 (2007), 123-138.

  • [2] RAZAK, Z.-ZULKIFLEE, K.et al : Off-Line Handwriting Text-Line Segmentation: a Review, International Journal of Computer Science and Network Security 8 No. 7 (2008), 12-20.

  • [3] LI, Y.-ZHENG, Y.-DOERMANN, D.-JAEGER, S. : A New Algorithm for Detecting Text Line in Handwritten Documents, In: 10th International Workshop on Frontiers in Handwriting Recognition 2006 IWFHR 2006, La Baule, France, pp. 35-40.

  • [4] LI, Y.-ZHENG, Y.-DOERMANN, D.-JAEGER, S. : Script- Independent Text Line Segmentation in Freestyle Handwritten Documents, IEEE Transactions on Pattern Analysis and Machine Intelligence 30 No. 8 (2008), 1313-1329.

  • [5] BUKHARI, S. S.-SHAFAIT, F.-BREUEL, T. M. : Script- Independent Handwritten Text-lines Segmentation using Active Contours, In: 10th International Conference on Document Analysis and Recognition 2009. ICDAR 2009, Barcelona, Spain, pp. 446-450.

  • [6] LI, Y.-ZHENG, Y.-DOERMANN, D.-JAEGER, S. : Script- Independent Text Line Segmentation in Freestyle Handwritten Documents, Technical report TR: LAMP-136/CS-4836/ UMIACS-2006-51/CFAR-1017, University of Maryland, College Park, 2006.

  • [7] BRODIĆ, D.-MILIVOJEVIĆ, Z. : Optimization of the Gaussian Kernel Extended by Binary Morphology for Text Line Segmentation, Radioengineering 19 No. 4 (2010), 718-724.

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

  • [9] KHASHMAN, A.-SEKEROGLU, B. : Document Image Binarisation Using a Supervised Neural Network, The International Journal of Neural Systems 18 No. 5 (2008), 405-418.

  • [10] GONZALEZ, R. C.-WOODS, R. E. : Digital Image Processing, 2nd ed., Prentice-Hall, USA, 2002.

  • [11] PREPARATA, F. P.-SHAMOS, M. I. : Computational Geometry: An Introduction, Springer-Verlag, Germany, 1985.

  • [12] RAMTEKE, R. J.-IMRAN, K. P.-MEHROTRA, S. C. : Skew Angle Estimation of Urdu Document Images: A Moments Based Approach, International Journal of Machine Learning and Computing 1 No. 1 (2011), 7-12.

  • [13] JÄHNE, B. : Digital Image Processing, 6th ed., Springer-Verlag, Germany, 2005.

  • [14] TERELL, G. R. : Mathematical Statistics: A Unified Introduction, Springer-Verlag, USA, 1999.

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

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

  • [17] BRODIĆ, D.-MILIVOJEVIĆ, D. R.-MILIVOJEVIĆ, Z. : Basic Test Framework for the Evaluation of Text Line Segmentation and Text Parameter Extraction, Sensors 10 No. 5 (2010), 5263-5279.

  • [18] POPOV, V. S. : Principles of Symmetry and Relative Errors of Instrumentation and Transducers, Automation and Remote Control 62 No. 5 (2001), 842-846.

  • [19] BRODIĆ, D. : The Evaluation of the Initial Skew Rate for Printed Text, J. Electrical Engineering 62 No. 3 (2011), 142-148.


Journal + Issues