High-precision orientation and skew detection for texts in scanned documents

This paper describes an approach towards an orientation and skew detection for texts in scanned documents. Before using OCR systems to obtain character information from images, a preprocessing stage, comprising a number of adjustments, has to be performed in order to obtain accurate results. One important operation that has to be considered is the skew correction, or deskewing, of the image, a fault that arises from an incorrect scanning process. This paper presents an iterative method for detecting the text orientation and skew angle, method based on histogram processing.