US 5,854,854 A · Skew detection and correction of a document image representation

Abstract

In a character recognition system, a method and apparatus for correcting the skew of a document image. Skew correction is typically performed during segmentation of the document image into text and non-text parts. Skew correction generally involves skew angle determination and correction of the document image based on the skew angle. A skew angle is determined through the steps of: providing a set of associated rectangles representing the document image, identifying a column edge associated with the set of associated rectangles, comparing rectangles from the set of associated rectangles to identify those that are in the same column and suitably far apart, calculating a tangential angle between the rectangles identified and identifying the most common tangential angle as the skew angle. Once the skew angle is determined, correction of the document image is made by constructing real skewed rectangles from corresponding extracted rectangles and rotating each of the real skewed rectangles around an origin coordinate for a distance based on the skew angle.

Claims11

Dependent claims

A method for correcting a skewed document image in a documentation system, said documentation system including a memory and a processor, said memory being coupled to said processor, said document image having one or more portions being stored in said memory, each of said one or more portions being represented by a set of rectangles, said method comprising the steps of:

said processor accessing said set of rectangles from said memory, wherein the size of each of the set of rectangles varies in response to the number of characters that said each rectangle represents;
said processor creating a column from said set of rectangles;
said processor identifying a column edge from said set of rectangles based on a histogram representation of positions of said set of rectangles;
said processor identifying a skew angle from a subset of said set of rectangles using said column edge, said subset of said set of rectangles comprising rectangles that are in said column;
for each rectangle (Ri) of said set of rectangles representing each one or more portions of said document image:
constructing a skewed rectangle from said skew angle and said rectangle Ri;
rotating said skewed rectangle based on said skew angle to correct skew for said rectangle Ri, such that a corrected skew image is generated.

4 more elements

Dependencies are inferred from the claim text.

Skew detection and correction of a document image representation

Life of this patent

Skew detection and correction of a document image representation

Life of this patent

Abstract

Claims11