INFORMATION CHANGE THE WORLD

International Journal of Information Technology and Computer Science(IJITCS)

ISSN: 2074-9007 (Print), ISSN: 2074-9015 (Online)

Published By: MECS Press

IJITCS Vol.7, No.11, Oct. 2015

Time and Accuracy Analysis of Skew Detection Methods for Document Images

Full Text (PDF, 419KB), PP.43-54


Views:124   Downloads:5

Author(s)

Sunita Mehta, Ekta Walia, Maitreyee Dutta

Index Terms

Document Image Processing;Skew detection;Skew correction;Discrete Wavelet transform;Principal Component Analysis;Hough transform;Radon transform;Moments

Abstract

Detecting skew angle in a document image has been an area of research interest for a long time. This paper presents an experimental analysis of various existing skew detection techniques involving methods such as Radon transform, Hough transform, Principal Component Analysis (PCA), PCA with Wavelet transform and Moments with Wavelet transform. Detailed analysis of existing skew detection method against the parameters time complexity, space complexity, robustness, accuracy, flexibility, etc. has been carried out for seven different categories of digital documents. The categories of these documents spans from those containing handwritten text in different languages, to the ones with both text and pictures. Radon transform is observed to be the fastest method when the image size is small and works with virtually all types of documents. It is an accurate method as well as works faster, even with the document containing pictures. PCA method is also faster than Hough transform for machine printed documents but used less for real time skew distortion due to its limitations. If the document image size is large, then Moments with Wavelet transform has better time complexity than other methods, but do not work well with documents containing images. Hough transform is the most accurate method, though it is computationally expensive.

Cite This Paper

Sunita Mehta, Ekta Walia, Maitreyee Dutta,"Time and Accuracy Analysis of Skew Detection Methods for Document Images", International Journal of Information Technology and Computer Science(IJITCS), vol.7, no.11, pp.43-54, 2015. DOI: 10.5815/ijitcs.2015.11.06

Reference

[1]Chandan Singh, Nitin Bhatia and Amandeep Kaur, “Hough transform based fast skew detection and accurate skew correction methods,” Pattern Recognition, vol. 41, pp.3528-3546, December 2008.

[2]N .Nandini, K. Srikanta Murthy, and G. Hemantha Kumar, “Estimation of skew Angle in binary document images using Hough transform,” Journal of  World Academy of Science, Engineering and Technology, vol. 32, pp. 50-55, August 2008.

[3]A.Amin and S.Fischer, “A document skew detection method using the Hough transform,” Pattern Analysis and Applications, vol. 3, pp.243-253, September 2000. 

[4]Stuart C.Hinds, James L.Fisher and Donald P.D’Amato, “A Document skew Detection Method Using Run – Length Encoding and the Hough Transform,” Proceedings of the Tenth International Conference on Pattern Recognition, pp.209 - 213, June 1990.

[5]S.N.Srihari and V.Govindraju, “Analysis of textual images using Hough transform,” Journal of Machine Vision and Applications, vol. 2, pp.141-153, 1989.

[6]V.N.Manjunath Aradhya, G.Hemantha Kumar and P.Shivakumara, “Skew detection technique for binary document images based on Hough transform,” International Journal of Information Technology, vol. 3, No. 3, pp. 194-200, 2006. 

[7]R.O. Duda, P.E. Hart, “Use of the Hough transformation to detect lines and curves in picture”, Magazine Communications of the ACM, pp. 11-15, vol. 15, No. 1, 1972.

[8]Gonzalez R.C, Woods, R.E., “Digital Image Processing”, 3rd Edition, Prentice Hall, 2008.

[9]Rajiv Kapoor, Deepak Bagai and T.S.Kamal, “A new algorithm for skew detection and correction”, Pattern Recognition Letters, vol. 25, pp.1215-1229, 2004.

[10]U.Pal and B.B.Chaudhuri ,”An improved document skew angle estimation technique”, Pattern Recognition Letters, vol. 25, pp.1215-1229,2004.

[11]P.Toft, “The Radon transform-Theory and Implementation”, Ph.D. thesis, Department of Mathematical Modeling, Technical University of Denmark, 1996.

[12]T.Steinherz, N. Intrator, E.Rivlin, “Skew detection via principal components analysis”, Proceedings of the International Conference on Document Analysis and Recognition, pp. 153-156, 1999.

[13]N. D. Modi, C.K. Modi, C.N. Paunwala ,S. Patnaik, “Skew correction for vehicle license plates using principal component of  Harris Corner Feature”, Proceedings of the IEEE International Conference on Communication Systems and Network  Technologies, pp. 339-343, 2011.

[14]S.Mehta,  E. Walia, and M. Dutta, “A new fast approach for Skew Estimation using Moments and Wavelet Transform”, International Conference on Image Processing Theory, Tools and Applications, pp. 221-226, 14-18   October 2014. 

[15]C.N.Paunwala, S. Patnaik, and M. Chaudhary, “An efficient skew detection of license plate images based on wavelet transform and principal component analysis,” in Proceedings of the IEEE International Conference on Signal and Image Processing, pp. 17-22, 2010.

[16]L.Shutao, S.Qinghua, and S.Jun, “Skew detection using wavelet decomposition and projection profile analysis,” Pattern Recognition Letters, vol. 28, Issue 5, pp.555-562, April 2007.

[17]Bishakha Jain and Mrinaljit Borah, “A comparison paper on skew detection of scanned document images based on horizontal and vertical projection profile analysis,” International Journal of Scientific and Research Publications, vol. 4, Issue 6, June 2014.

[18]D.Brodic, C.A.Maluckov, and L.Peng, “Estimation of the text skew in the old Printed documents,” International Journal of Computer Communication, vol. 8, No. 5, pp. 673-680, Oct 2013. 

[19]Shivakumara, G.Hemantha Kumar ,and H.S.Varsha, “A new moments based skew estimation technique using pixels in the word for binary document images,”  Proceedings of the Eight IEEE International Conference on Document Analysis and Recognition, pp. 151-156, vol. 1, August 2005. 

[20]Mandip Kaur and Simpel Jindal, “An integrated skew detection and correction using fast Fourier transform and DCT,” International Journal of Scientific and Technology, vol. 2, pp. 164-169, December 2013.

[21]Deepak Kumar and Dalwinder Singh, “Modified approach of Hough transform for skew detection and correction in document images,” International Journal of Research in Computer Science, vol. 2, Issue 3, pp. 37-40, 2012.

[23]Sepideh Barekat Rezaei, Abdolhossein Sarrafzadeh and Jamshid Shanbehzadeh, “Skew detection of scanned document images,” Proceedings of the International MultiConference of Engineers and Computer Scientists, vol. I, pp. 1-6, March 2013.

[24]Khalil Ibrahim Alsaif and Montaha Tariq Alsarraj, “New technique for skew angle of text in image document,” International Journal of Information Technology and Business Management, vol.16, No.1, pp. 102-110, August 2013. 

[25]H.Yan, “Skew correction of document images using interline cross-correlation,” Journal of Graphic Models and Image Processing, vol. 55, pp. 538-543, November 1993.

[26]A.K. Das, B. Chanda, “A fast algorithm for skew detection of document images using morphology”, International Journal on Document Analysis and Recognition, vol. 4, pp. 109–114, 2001.

[27]Ruby Singh, Ramandeep Kaur, “Improved skew detection and correction approach using Discrete Fourier algorithm”, International Journal of soft computing and Engineering, vol. 3, Issue 4, pp. 5-7, September 2013.