Title :
A new boundary growing and Hough transform based approach for accurate skew detection in binary document images
Author :
Shivakumar, P. ; Kumar, G. Hemantha ; Guru, D.S. ; Nagabhushan, P.
Author_Institution :
Dept. of Studies in Comput. Sci., Mysore Univ., India
Abstract :
Skew angle estimation is an important component of an optical character recognition (OCR) and document analysis systems (DAS). In this paper, a novel and efficient (in terms of accuracy and computations) method to estimate skew angle of a scanned document image is proposed. The proposed technique works based on fixing a boundary for connected components and growing boundaries. The technique uses Hough transform (HT) to estimate skew angles. However, the technique works based on the assumption that the space between the two adjacent text lines is greater than the space between the successive characters present in a text line. The proposed method is compared with other existing methods. The experimental results are also presented.
Keywords :
Hough transforms; document image processing; optical character recognition; binary document images; document analysis systems; optical character recognition; skew angle estimation; skew detection; Application software; Character recognition; Histograms; Image converters; Nearest neighbor searches; Noise reduction; Optical character recognition software; Optical detectors; Optical devices; Text analysis;
Conference_Titel :
Intelligent Sensing and Information Processing, 2005. Proceedings of 2005 International Conference on
Print_ISBN :
0-7803-8840-2
DOI :
10.1109/ICISIP.2005.1529437