Skew Detection based on Bounding Edge Approximation
P. Malathi · IOSR Journal of Computer Engineering · 2014
Any paper document when converted to electronic form through standard digitizing devices, like scanners, is subject to a small tilt or skew.With recent advances of hand-held devices such as cell-phones, Personal Digital Assistants (PDA), etc. having built-in digital cameras, a new trend of document capturing has emerged.Because of the non-contact nature of digital cameras attached to these handheld devices, acquired images very often suffer from skew distortion.A de-skewed document allows a more compact representation of its components, particularly text objects, such as words, lines, and paragraphs.This simplified representation leads to more efficient, robust, as well as simpler algorithms for document image analysis including optical character recognition (OCR).This paper presents a new method for automatic skew detection in images using heuristic approach .The proposed algorithm is fast as well as independent of the scripting language.