Estimation of Skew Angle in Binary Document Images Using Hough Transform

Authors: Nandini N., Srikanta Murthy K., G. Hemantha Kumar

Abstract:

This paper includes two novel techniques for skew estimation of binary document images. These algorithms are based on connected component analysis and Hough transform. Both these methods focus on reducing the amount of input data provided to Hough transform. In the first method, referred as word centroid approach, the centroids of selected words are used for skew detection. In the second method, referred as dilate & thin approach, the selected characters are blocked and dilated to get word blocks and later thinning is applied. The final image fed to Hough transform has the thinned coordinates of word blocks in the image. The methods have been successful in reducing the computational complexity of Hough transform based skew estimation algorithms. Promising experimental results are also provided to prove the effectiveness of the proposed methods.

Keywords: Dilation, Document processing, Hough transform, Optical Character Recognition, Skew estimation, and Thinning.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1071884

References:

[1] Baird H. S., "The skew angle of printed documents", Proc. of SPSE 40th Symposium on Hybrid imaging systems, Rochester, NY, 1987, pp 739- 743.
[2] Postl W., "Detection of linear oblique structure and skew scan in digitized documents", Proc. of Int. Conf. on Pattern Recognition, 1986, pp 687-689.
[3] Yan, H., "Skew correction of document images using interline crosscorrelation", Computer Vision, Graphics, and Image Processing 55, 1993, pp 538-543.
[4] A. Hashizume, P. S. Yeh, A. Rosenfeld, "A method of detecting the orientation of aligned components", Pattern Recognition Letters, 1996, pp. 125-132.
[5] Shivakumara P., S. Guru, G. Hemantha Kumar, P Nagabhushan, "Skew detection in Binary document image using Linear Regression Analysis", proc. Of National Conf. on Advanced Computer Application NCAC- 2002, Pollachi, India 2002, pp 41-46.
[6] Najman L., "Using mathematical morphology for document skew estimation", SPIE Document Recognition and retrievals XI vol. 5296, 2004, pp 182-191.
[7] Srihari S. N. and Govindraju V., "Analysis of textual images using Hough Transform", Machine vision Applications 2, 1989, pp 141-153.
[8] Le D S, Thoma G R and Wechsler H, "Automatic page orientation and skew angle detection for binary document images." Patter Recognition 27, 1994, pp. 1325 - 1344.
[9] B. Yu and A. K. Jain, "A robust and fast skew detection algorithm for generic documents," Pattern Recognition, 29, no. 10, 1996, pp. 1599- 1630.
[10] Pal U and Chaudhari B. B, "An improved document skew angle estimation technique", Pattern Recognition Letters, Vol. 17,1996, pp. 899-904.
[11] B. V. Dhandra, V. S. Malemath, Mallikarjun H, Ravindra Hegadi, "Skew Detection in Binary Image Documents Based on Image Dilation and Region labeling Approach", The 18th International Conference on Pattern Recognition (ICPR'06), 2006.
[12] Manjunath Aradhya V N, Hemantha Kumar G. and Shivakumara P, "Skew detection technique for binary document images based on Hough transform", International Journal of Information Technology, Vol. 3, 2006.
[13] M Ahmed and R Ward, "Rotation Invariant Rule-Based Thinning Algorithm for Character Recognition", IEEE. Trans. Pattern Analysis and Machine Interlligence, vol. 24, No. 12, December 2002.
[14] Gonzalez R., Woods, Digital Image Processing, Addison-Wesley Publishing Company. 2nd Ed. 2002.
[15] D.R.Ramesh Babu Piyush M Kumat Mahesh D Dhannawat,"Skew Angle Estimation and Correction of Hand Written, Textual and Large areas of Non-Textual Document Images: A Novel Approach", IPCV 2006, 510-515.
[16] Wikipedia - Hough transform source URL:http://en.wikipedia.org/wiki/Hough_transform