Linear Regression-Based Skew Correction of Handwritten Words in Indian Languages

Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 704)


Skew corrected text lines in multi-oriented handwritten documents often contain words that are not properly aligned. Most segmentation algorithms fail to correctly segment skewed words into constituent characters. So, skew correction of words in a text line is as important as skew correction of a text line in a document. In the present work, we propose a method that uses linear curve fitting for estimating and correcting skew present in handwritten words. This method efficiently detects and corrects skew in four Indian languages, namely Bangla, Hindi, Marathi and Panjabi. The proposed method is able to handle skewed word images to an extent of \(\pm {50^{\circ }}\) and provides accurate result even when the \(m\bar{a}tr\bar{a}\) is discontinuous. We have compared our method with existing ones to show the efficacy of the proposed method.


Curve fitting Handwritten words Indian languages Skew correction Skew estimation 



The authors wish to thank Deepika Gupta, Junior Research Fellow, Department of Computer Science and Engineering, IIT(ISM), Dhanbad, for collecting, organizing and providing the Marathi data set used in this work.


  1. 1.
    Shi, Z., Govindraju, V.: Skew Detection for Complex Document Images Using Fuzzy Runlength. In: Proceedings of the International Conference on Document Analysis and Recognition, pp. 715–719, (2003)Google Scholar
  2. 2.
    Srihari, S.N., Govindraju, V.: Analysis of textual image using the Hough transform. Machine Vision Applications, vol. 2, pp. 141–153, (1989)Google Scholar
  3. 3.
    Chin, A.H.W., Jennings, A.: Skew detection in handwritten scripts. In: Speech and Image Technologies for computation and Telecommunications, pp. 319–322, (1997)Google Scholar
  4. 4.
    Postl, W.: Detection of linear oblique structures and skew scan in digitized documents. In: Proceedings of the International Conference on Pattern Recognition, pp. 687–689, (1986)Google Scholar
  5. 5.
    Sarfraz, M., Zidouri, A., Shahab, S.A.: A novel approach for skew estimation of document images in OCR system. In: Proceedings of the International Conference on Computer Graphics, Imaging and Vision: New Trends, pp. 175–180, (2005)Google Scholar
  6. 6.
    Bagdanov, A., Kanai J.: Projection profile based Skew Estimation Algorithm for JBIG Compressed Images. In: Proceedings of the International Conference on Document Analysis and Recognition, pp. 401–405, (1997)Google Scholar
  7. 7.
    Bag, S., Bhowmick, P., Harit, G., Biswas, A.: Character segmentation of handwritten Bangla text by vertex characterization of isothetic covers. In: Proceedings of the National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics, pp. 21–24, (2011)Google Scholar
  8. 8.
    Bag, S., Krishna, A.: Character Segmentation of Hindi Unconstrained Handwritten Words. In: Proceedings of the International Workshop on Combinatorial Image Analysis, pp. 247–260, (2015)Google Scholar
  9. 9.
    Bhowmik, T.K., Roy, A., Roy, U.: Character segmentation for handwritten Bangla words using artificial neural network. In: Proceedings of the IAPR TC3 NNLDAR, (2005)Google Scholar
  10. 10.
    Roy, A., Bhowmik, T.K., Parui, S.K., Roy, U.: A novel approach to skew detection and character segmentation for handwritten Bangla words. In: Digital Image Computing: Techniques and Applications, pp. 30–30, (2005)Google Scholar
  11. 11.
    Malakar, S., Seraogi, B., Sarkar, R., Das, N., Basu, S., Nasipuri, M.: Two-stage skew correction of handwritten Bangla document images. In: Proceedings of the International Conference on Emerging Applications of Information Technology, pp. 303–306, (2012)Google Scholar
  12. 12.
    Otsu, N.: A threshold selection method from Gray level histogram. IEEE Transaction on System, Man, Cybernetics, vol. 19, pp. 62–66, (1978)Google Scholar
  13. 13.
    Rosenfeld, A., Kak, A.: Digital picture processing, \(2^{nd}\) Edition, vol. 1 and 2, Academic press, New York, (1982)Google Scholar
  14. 14.
    Bhattacharya, U., Shridhar, M., Parui, S.K., Sen, P.K., Chaudhuri, B.B.: Offline recognition of handwritten Bangla characters: an efficient two-stage approach. Pattern Analysis and Applications, vol. 15, no. 4, pp. 445–458, (2012)Google Scholar
  15. 15.
    Basu, S., Chaudhury, C., Kundu, M., Nasipuri, M., Basu, D.K.: Text line extraction from multi skewed handwritten documents. Pattern Recognition, vol. 40, no. 6, pp. 1825–1839, (2007)Google Scholar
  16. 16.
    Das, N., Halder, C., Obaidullah, S.M., Roy, K., Santosh, K.C.: PHDIndic_11: page-level handwritten document image dataset of 11 official Indic scripts for script identification. Multimedia Tools and Applications, pp. 1–36, (2017)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  1. 1.Department of Computer Science and EngineeringIndian Institute of Technology (ISM)DhanbadIndia

Personalised recommendations