Comparative study of skew detection algorithms

Document image processing has become an increas- ingly important technology in the automation of office documentation tasks. Automatic document scanners such as text readers and op- tical character recognition (OCR) systems are an essential compo- nent of systems capable of those tasks. One of the problems in this field is that the document to be read is not always placed correctly on a flat-bed scanner. This means that the document may be skewed on the scanner bed, resulting in a skewed image. This skew has a detrimental effect on document analysis, document under- standing, and character segmentation and recognition. Conse- quently, detecting the skew of a document image and correcting it are important issues in realizing a practical document reader. We describe a new algorithm for skew detection. We then compare the performance and results of this skew detection algorithm to other published methods from O'Gorman, Hinds, Le, Baird, Postl, and Ak- iyama. Finally, we discuss the theory of skew detection and the different approaches taken to solve the problem of skew in docu- ments. The skew correction algorithm we propose has been shown to be extremely fast, with run times averaging under 0.25 CPU sec- onds to calculate the angle on a DEC 5000/20 workstation. © 1996 SPIE and IS&T.