A document skew detection method using run-length encoding and the Hough transform

TLDR: By creating a burst image from the original document image, the processing time of the Hough transform can be reduced by a factor of as much as 7.4 for documents with gray-scale images and interline spacing can be determined more accurately.

Abstract: As part of the development of a document image analysis system, a method, based on the Hough transform, was devised for the detection of document skew and interline spacing-necessary parameters for the automatic segmentation of text from graphics. Because the Hough transform is computationally expensive, the amount of data within a document image is reduced through the computation of its horizontal and vertical black runlengths. Histograms of these runlengths are used to determine whether the document is in portrait or landscape orientation. A gray scale burst image is created from the black runlengths that are perpendicular to the text lines by placing the length of the run in the run's bottom-most pixel. By creating a burst image from the original document image, the processing time of the Hough transform can be reduced by a factor of as much as 7.4 for documents with gray-scale images. Because only small runlengths are input to the Hough transform and because the accumulator array is incremented by the runlength associated with a pixel rather than by a factor of 1, the negative effects of noise, black margins, and figures are avoided. Consequently, interline spacing can be determined more accurately. >