Document skew detection based on local region complexity

A new method is proposed for detecting skew in document images which contain a mixture of text areas, photographs, figures, charts, and tables. Two basic ideas are introduced in the method. One idea is that a new parameter is used for skew detection to discern the orientation of text lines in document images. This parameter is based on the document image complexity and is obtained from the number of transitions from white to black pixels or vice versa. The other idea is that skew is detected in local regions in which only text lines are expected. Such local regions are extracted from a document image automatically and the obtained skew angle is defined as the overall document skew. Document skew has been measured in experiments with an error of 0.12 degrees on the average for all test documents