Robust Skew Estimation Technique Based on Boundary Growing and Radon Transform

Document image processing has become an increasingly important technology in the automation of office documentation tasks. Automatic document scanners such as text readers and OCR (Optical Character Recognition) systems are an essential component of those tasks. Hence, the problem in this field is that the document to be read is not always placed correctly on a flat bed scanner, resulting in a skewed document. Hence in this paper we present a new skew estimation technique for binary document images using boundary growing and Radon transform. This is required to enhance the ability of the document analysis system through Optical Character Recognition. The Boundary Growing (BG) is used to extract the text line from skewed document. The resultant extracted text line from the skewed document images are then applied for Radon transform for estimation of the skew angle. Several experiments have been conducted on various types of documents such as documents containing English Documents Journals Text-Book 1 2 is accurate compared to the results of well-known existing methods. Keywords: Optical Character Recognition (OCR), Skew Detection, Boundary Growing, Radon Transform, Document Processing,