Skew Angle Estimation and Correction for Noisy Document Images

  • M. Manomathi
  • S. Chitrakala
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 192)


Document skew commonly occurs during document scanning; it should be avoided because it dramatically reduces the accuracy of the OCR. Noise removal is an important procedure before on going further processing. This paper describes an approach towards noise removal, skew detection and correction for text in scanned documents. Preprocessing is a stage, comprising number of adjustments in order to obtain the noise reduced results, and then the skew angle is estimated. Instead of deriving a skew angle from the text lines, the proposed method uses various types of visual content of image skews, and HDT algorithm is used to select the useful image region dynamically. A bootstrap estimator is finally employed to combine various cues on local image blocks. Once the skew angle is being estimated it has to be rotated in the opposite direction in order to correct the skew angle.


Bagging estimator Visual content Preprocessing 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Amin, A., Fischer, S.: A document skew detection method using Hough transform. Pattern Anal. Appl. 3(3), 243–253 (2000)CrossRefzbMATHGoogle Scholar
  2. 2.
    Yuan, B., Lim, C.: Skew Estimation for Scanned Documents from Noises. Centre for Remote Imaging. Sensing and Processing Department of Computer Science, School of Computing National University of Singapore, Models Image Process. 41(6), 234–243 (2005)Google Scholar
  3. 3.
    Faisal, S.H., Daniel, K.V., Thomas, B.M.: Response to Projection Methods Require Black Border Removal. Pattern Recognition. Lett. 28(7), 155–162 (2009)Google Scholar
  4. 4.
    Gaofeng, M.G., Nanning, Z.A., Zhang, Y., Song, Y.: Circular Noises Removal from Scanned Document Images. Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, China (2007)Google Scholar
  5. 5.
    Liu, H., Wu, Q., Zha, H.B., Liu, X.P.: Skew detection for complex Document images using robusts border lines in both text and non-text regions. Pattern Recognit. Lett. 29(13), 1893–1900 (2008)CrossRefGoogle Scholar
  6. 6.
    Lu, Tan: A nearest-neighbor chain based approach to skew Estimation in document images. Pattern Recognit. Lett. 24(14), 2315–2323 (2003)CrossRefGoogle Scholar
  7. 7.
    Martin, Pattichis: Characterization of Scanning Noise and Quantization on Texture Feature Analysis. In: Computer, University of New Mexico, Albuquerque, vol. 25(7), pp. 10–22 (2004)Google Scholar
  8. 8.
    Mudit, A.L., David Dorman, D.C.: Clutter Noise Removal in Binary Document Images. In: 10th International Conference on Document Analysis and Recognition, Computer, vol. 25(7), pp. 110–212 (2009)Google Scholar
  9. 9.
    Sarfraz, M., Zidouri, A., Shahab, S.A.: Novel Approach for Skew Estimation of Document Images. In: OCR SystemGoogle Scholar
  10. 10.
    Shen, L., Sun, L.: Skew detection using wavelet decomposition And projection profile analysis. Pattern Recognition Lett. 28(5), 555–562 (2007)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • M. Manomathi
    • 1
  • S. Chitrakala
    • 1
  1. 1.Dept. of Computer Science & Engineering, Easwari Engineering CollegeAnna universityChennaiIndia

Personalised recommendations