Abstract
During document scanning, skew is inevitably introduced into the incoming document image. Presence of additional modified characters, which get plugged in as extensions and remain as disjointed protrusions of a main character is really challenging in estimating inclination in skewed documents made up of texts in south Indian languages (Kannada, Telugu, Tamil and Malayalam). In this paper, we present a novel script independent (for south Indian) skew estimation technique based on Gaussian Mixture Models (GMM). The Expectation-Maximization (EM) algorithm is used to learn the mixture of Gaussians. Subsequently the cluster means are subjected to moments to estimate the skew angle. Experiments on printed and handwritten documents corrupted by noise is done. Our method shows significantly improved performance as compared to other existing methods.
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Basu, S., Chaudhuri, C., Kundu, M., Narsipuri, M., Basu, D.K.: Text line extraction from multi-skewed handwritten documents. Pattern Recognition 40(6), 1825–1839 (2007)
Bishop, C.M.: Pattern Recognition and Machine Learning. Springer, Heidelberg (2006)
Gonzalez, R.C., Woods, R.E.: Digital Image Processing, 2nd edn. Pearson Education (2002)
Yan, H.: Skew correction of document images using interline cross-correlation. Computer Vision, Graphics, and Image Processing 55, 538–543 (1993)
Kapoor, R., Deepak, Kamal.: A new algorithm for skew detection and correction. Pattern Recognition Letters 25, 1215 (2004)
Lu, Y., Tan, C.L.: A nearest neighbor chain based approach to skew estimation in document images. Pattern Recognition Letters 24, 2315–2323 (2003)
Manjunath Aradhya, V.N., Hemantha Kumar, G., Shivakumara, P.: An accurate and efficient skew estimation technique for south indian documents. International Journal of Robotics and Automation (in press)
Baird, H.S.: The skew angle of printed documents. In: Proceedings of Conference Society of Photographic Scientists and Engineers, pp. 14–21 (1987)
Hou, H.S.: Digital Document Processing. Wisely, New York (1983)
Le, D.S., Thoma, G.R., Wechsler, H.: Automatic page orientation and skew angle detection for binary document images. Pattern Recognition 27, 1325–1344 (1994)
Srihari, S.N., Govindaraju, V.: Analysis of textual images using the hough transform. Machine Vision and Applications 2, 141–153 (1989)
Akiyama, T., Hagita, N.: Automated entry system for printed documents. Pattern Recognition 23(11), 1141–1158 (1990)
Pal, U., Chaudhuri, B.B.: An improved document skew angle estimation technique. Pattern Recognition Letters 17, 899–904 (1996)
Postl, W.: Detection of linear oblique structures and skew scan in digitized documents. In: Proceedings 8th International Conference on Pattern Recognition, pp. 687–689 (1986)
Yang, C., Wang, S., Heng, L.: Skew detection and correction in document images based on straight-line fitting. Pattern Recognition Letters 24, 1871 (2003)
Yu, B., Jain, A.K.: A robust and fast skew detection algorithm for generic documents. IEEE Transactions on Pattern Analalysis and Machine Intelligence 29(10), 1599–1629 (1996)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Aradhya, V.N.M., Rao, A., Kumar, G.H. (2007). Language Independent Skew Estimation Technique Based on Gaussian Mixture Models: A Case Study on South Indian Scripts. In: Ghosh, A., De, R.K., Pal, S.K. (eds) Pattern Recognition and Machine Intelligence. PReMI 2007. Lecture Notes in Computer Science, vol 4815. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-77046-6_60
Download citation
DOI: https://doi.org/10.1007/978-3-540-77046-6_60
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-77045-9
Online ISBN: 978-3-540-77046-6
eBook Packages: Computer ScienceComputer Science (R0)