An Improved Method for Text Segmentation and Skew Normalization of Handwriting Image

  • Abhishek BalEmail author
  • Rajib Saha
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 518)


This paper proposed an off-line cursive handwriting segmentation method and an efficient skew normalization process of the handwritten document. The proposed segmentation method based on horizontal and vertical projection, which has been already used for different purposes in handwriting analysis. But to tolerate the text lines overlapping and multi-skewed text lines, present work implements modified version of horizontal and vertical projection, which can segment the text lines and words even if text lines are overlapped. Present work also proposed a skew normalization method which is based on orthogonal projection toward the x-axis. The proposed method was tested on more than 550 text images of IAM database and sample handwriting image which are written by the different writer on the different background. The experimental result shows that proposed algorithm achieves more than 96% accuracy.


Document image Feature extraction Line segmentation Word segmentation Skew normalization Orthogonal projection 



The authors sincerely express their gratitude to TEQIP-II & Dr. Arup Kumar Bhaumik, Principal of RCC Institute of Information Technology College, for giving regular encouragement in doing research in the field of image processing.


  1. 1.
    Stéphane Nicolas, Thierry Paquet, Laurent Heutte: Text Line Segmentation in Handwritten Document Using a Production System. In: Proceedings of the 9th Int’l Workshop on Frontiers in Handwriting Recognition (IWFHR-9 2004), IEEE, 2004.Google Scholar
  2. 2.
    Khaled Mohammed bin Abdl, Siti Zaiton Mohd Hashim: Handwriting Identification: a Direction Review. In: IEEE International Conference on Signal and Image Processing Applications (2009), 978-1-4244-5561-4/09.Google Scholar
  3. 3.
    N. Otsu: A threshold selection method from Gray level histogram. In: IEEE Transaction on system, Man, Cybernetics (1979), VOL. SMC-9, pp. 62–66.Google Scholar
  4. 4.
    W. Niblack: An Introduction to Digital Image Processing. In: Englewood Cliffs, New Jersey Prentice-Hall (1986).Google Scholar
  5. 5.
    Rejean Plamondon, Sargur N. Srihari: On-Line and Off-Line Handwriting Recognition. In: A Comprehensive Survey. IEEE transactions on pattern analysis and machine intelligence (2000), vol. 22, no. 1.Google Scholar
  6. 6.
    Yan Solihin, C.G. Leedham: Noise and Background Removal from Handwriting Images, IEEE (1997).Google Scholar
  7. 7.
    Atena Farahmand, Abdolhossein Sarrafzadeh, Jamshid Shanbehzadeh: Document Image Noise and Removal Methods. In: Proceedings of the International MultiConference of Engineers and Computer Scientists, Hong Kong (2013), Vol I.Google Scholar
  8. 8.
    G. Story, L. O’Gorman, D. Fox, L. Schaper, H. Jagadish: The rightpages image-based electronic library for alerting and browsing. In: IEEE Computer Society Press Los Alamitos, CA, USA (1991), vol. 25, no. 9, pp. 17– 26.Google Scholar
  9. 9.
    N. Premchaiswadi, S. Yimgnagm and W. Premchaiswadi: A scheme for salt and pepper noise reduction and its application for ocr systems. In: Wseas Transactions On Computers (2010), vol. 9, pp. 351–360.Google Scholar
  10. 10.
    Andria, G. Savino, M. Trotta, A.: Application of Wigner-Ville distribution to measurements on transient signals. In: Instrumentation and Measurement, IEEE Transactions (1994), vol. 43, no. 2, pp. 187–193.Google Scholar
  11. 11.
    U.-V. Marti, H. Bunke: Text Line Segmentation and Word Recognition in a System for General Writer Independent Handwriting Recognition. In: IEEE, 0-7695-1263-1/01 (2001).Google Scholar
  12. 12.
    Partha Pratim Roy, Prasenjit Dey, Sangheeta Roy, Umapada Pal, Fumitaka Kimura: A Novel Approach of Bangla Handwritten Text Recognition using HMM. In: 14th International Conference on Frontiers in Handwriting Recognition (2014), IEEE, 2167-6445/14.Google Scholar
  13. 13.
    Matthias Zimmermann, Horst Bunke: Automatic Segmentation of the IAM Off-line Database for Handwritten English Text, IEEE, 1051:465:l/02 (2002).Google Scholar
  14. 14.
    Florence Luthy, Tamas Varga, Horst Bunke: Using Hidden Markov Models as a Tool for Handwritten Text Line Segmentation. In: Ninth International Conference on Document Analysis and Recognition (ICDAR 2007), 0-7695-2822-8/07.Google Scholar
  15. 15.
    Themos Stafylakis, Vassilis Papavassiliou, Vassilis Katsouros, George Carayannis: Robust Text-Line and Word Segmentation for Handwritten Documents Images. In: Greek Secretariat for Research and Technology under the program (2008), IEEE.Google Scholar
  16. 16.
    A. Sánchez, P.D. Suárez, C.A.B. Mello, A.L.I. Oliveira, V.M.O. Alves: Text Line Segmentation in Images of Handwritten Historical Documents. In: Image Processing Theory, Tools & Applications, IEEE, 978-1-4244-3322-3/08 (2008).Google Scholar
  17. 17.
    Jija Das Gupta, Bhabatosh Chanda: A Model Based Text Line Segmentation Method for Off-line Handwritten Documents. In: 12th International Conference on Frontiers in Handwriting Recognition, IEEE, 978-0-7695-4221-8/10 (2010).Google Scholar
  18. 18.
    Mohammed Javed, P. Nagabhushan, B.B. Chaudhuri: Extraction of Line-Word-Character Segments Directly from Run-Length Compressed Printed Text-Documents, Jodhpur (2013), IEEE, ISBN: 978-1-4799-1586-6, INSPEC: 14181850, 18–21.Google Scholar
  19. 19.
    Xi Zhang, Chew Lim Tan: Text Line Segmentation for Handwritten Documents Using Constrained Seam Carving. In: 2014 14th International Conference on Frontiers in Handwriting Recognition, IEEE, 2167-6445/14 (2014).Google Scholar
  20. 20.
    Matthias Zimmermann, Horst Bunke: Hidden Markov Model Length Optimization for Handwriting Recognition Systems. In: Proceedings of the Eighth International Workshop on Frontiers in Handwriting Recognition (IWFHR 2002), IEEE, 0-7695-1692-0/02.Google Scholar
  21. 21.
    Joan Pastor-Pellicer, Salvador Espana-Boquera, Francisco Zamora-Martınez, Marıa Jose Castro-Bleda: Handwriting Normalization by Zone Estimation using HMM/ANNs. In: 14th International Conference on Frontiers in Handwriting Recognition (2014), IEEE, 2167-6445/14.Google Scholar
  22. 22.
    Fotini Simistira, Vassilis Papavassiliou, Themos Stafylakis: Enhancing Handwritten Word Segmentation by Employing Local Spatial Features. In: 2011 International Conference on Document Analysis and Recognition (2011), IEEE, 1520-5363/11.Google Scholar
  23. 23.
    Wesley Chin, Man Harvey, Andrew Jennings: Skew Detection in Handwritten Scripts. In: Speech and Image Technologies for Computing and Telecommunications, IEEE TENCON (1997).Google Scholar
  24. 24.
    Srihari, S.N., Govindraju: Analysis of textual image using the Hough transform. In: Machine Vision Applications (1989) Vol. 2 141–153.Google Scholar
  25. 25.
    Champa H N, K R AnandaKumar: Automated Human Behavior Prediction through Handwriting Analysis. In: 2010 First International Conference on Integrated Intelligent Computing, IEEE, 978-0-7695-4152-5/10 (2010).Google Scholar
  26. 26.
    Abdul Rahiman M, Diana Varghese, Manoj Kumar G: Handwritten Analysis Based Individualistic Traits Prediction. In: International Journal of Image Processing (2013), Volume 7 Issue 2.Google Scholar
  27. 27.
    Abhishek Bal, Rajib Saha: An Improved Method for Handwritten Document Analysis using Segmentation, Baseline Recognition and Writing Pressure Detection. In: 6th IEEE International Conference on Advances in Computing and Communications (ICACC-2016), Sept 6–8, 2016, Volume 93, Pages 403–415, doi:
  28. 28.
    Subhash Panwar, Neeta Nain: Handwritten Text Documents Binarization and Skew Normalization Approaches. In: IEEE Proceedings of 4th International Conference on Intelligent Human Computer Interaction, Kharagpur, India (2012).Google Scholar
  29. 29.
    A. Roy, T.K. Bhowmik, S.K. Parui, U. Roy: A Novel Approach to Skew Detection and Character Segmentation for Handwritten Bangla Words. In: Proceedings of the Digital Imaging Computing: Techniques and Applications, IEEE, 0-7695-2467-2/05 (2005).Google Scholar
  30. 30.
    Subhash Panwar, Neeta Nain: A Novel Approach of Skew Normalization for Handwritten Text Lines and Words. In: Eighth International Conference on Signal Image Technology and Internet Based Systems, IEEE, 978-0-7695-4911-8/12 (2012).Google Scholar
  31. 31.
    Jija Das Gupta, Bhabatosh Chanda: Novel Methods for Slope and Slant Correction of Off-line Handwritten Text Word. In: Third International Conference on Emerging Applications of Information Technology (2012), IEEE, 978-1-4673-1827-3/12.Google Scholar
  32. 32.
    Abhishek Bal, Rajib Saha: An Efficient Method for Skew Normalization of Handwriting Image. In: 6th IEEE International Conference on Communication Systems and Network Technologies, Chandigarh (2016), pp. 222–228, ISBN: 978-1-4673-9950-0.Google Scholar
  33. 33.
    M Sarfraj, Z Rasheed: Skew Estimation and Correction of Text using Bounding Box. In: Fifth IEEE conference on Computer Graphics, Imaging and Visualization (2008), pp. 259–264.Google Scholar
  34. 34.
    V. Papavassiliou, T. Stafylakis, V. Katsouros, G. Carayannis: Handwritten document image segmentation into text lines and words. In: Pattern Recognition, vol. 43, pp. 369-377, doi: 10.1016/j.patcog (2009).
  35. 35.
    Marcus Liwicki and Horst Bunke: IAM-OnDB - an On-Line English Sentence Database Acquired from Handwritten Text on a Whiteboard. In: Proceedings of the 2005 Eight International Conference on Document Analysis and Recognition (ICDAR 2005), IEEE, 1520-5263/05.Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  1. 1.Department of Computer Science & EngineeringRCC Institute of Information TechnologyKolkataIndia

Personalised recommendations