Autors: Draganov, I. R., Popova, A. A.
Title: Rotation Angle Estimation of Scanned Handwritten Cursive Text Documents
Keywords: handwritten text recognition, angle estimation

Abstract: In this paper we propose an algorithm that estimates the rotation angle presenting in scanned images of handwritten cursive text. It combines a technique of tracking the separate words connectivity, narrowing the range of possible rotation angles to be checked and the extra obtained results are found useful in the following stages of a complete handwritten text recognition system.


  1. Glauberman, M., 1956, Character Recognition for Business Machines, Electronics, Volume 29, pp. 132-136
  2. Pal, U., S. Sinha, B. Chaudhuri, 2002, Multi-Oriented Text Lines Detection and Their Skew Estimation. In: Proceedings of the Third Indian Conference on Computer Vision, Graphics & Image Processing (ICVGIP 2002), Ahmadabad, India, 16-18 December 2002, <>, Allied Publishers Private Limited
  3. Shivakumara, P., G. Kumar, D. Guru, P. Nagabhushan, 1950, Skew Estimation of Binary Document Images Using Static and Dynamic Thresholds Useful for Document Image Mosaicing. In: Conf. Proc. of the National Workshop on IT Services and Applications (WITSA 2003), New Delhi, India, 27-28 February 2003, <>,
  4. Clark, P., M. Mirmehdi, 2002, On the Recovery of Oriented Documents from Single Images. In: Conf. Proc. of the Advanced Concepts for Intelligent Vision Systems, Ghent, Belgium, 9-11 September 2002, <>,
  5. Messelodi, S., C. Modena, 1999, Automatic Identification and Skew Estimation of Text Lines in Real Scene Images, Pattern Recognition, Volume Vol. 32, No. 5, pp. 789-808


41st International Scientific Conference on Information, Communication and Energy Systems and Technologies (ICEST 2006), pp. 177-180, 2006, Bulgaria, KING Ltd., ISBN 978-954-9518-37-5

Full text of the publication

Вид: публикация в международен форум, индексирана в Google Scholar