Image skew detection apparatus and methods

• US 8,064,729 B2
• Filed: 04/03/2008
• Issued: 11/22/2011
• Est. Priority Date: 04/03/2008
• Status: Active Grant

• Current Assignee: Seiko Epson Corporation (Seiko Group)
• Original Assignee: Seiko Epson Corporation (Seiko Group)
• Inventors: Li, Jia, Zhou, Hui
• Primary Examiner(s): COUSO, YON JUNG
• Application Number:
  US12/062,430
• Publication Number:
  US 20090252437A1
• Time in Patent Office: 1,328 Days
• Field of Search: 382/289, 382/290, 382293-296
• US Class Current: 382/289
• CPC Class Codes: G06V 30/1478 of characters or characters lines

Abstract

Methods and apparatus for detecting skew in a document image, such as a check image, to produce a de-skewed image are described. One example method includes detecting one or more lines in the image and determining whether the one or more lines are reliable. Reliability of a line may be based on at least one of line length, straightness, and the presence of holes in the line. If one or more lines are reliable, the method may calculate a skew angle of the image based on the one or more reliable lines'"'"' orientations with respect to an orientation of the image. A comparison may also be made between lines detected in different regions of the check to determine if a difference between skew angles corresponding to each of the compared lines is lower than an error threshold.

Claims

1. A method for detecting skew in an image to produce a de-skewed image, the method comprising:

scanning a first region of the image for a first group of one or more lines;

scanning a second region of the image for a second group of one or more lines if none of the lines in the first group of one or more lines is reliable; and

if none of the lines in the second group of one or more lines is reliable, using a processor to;

compare an angle of a line in the first group of one or more lines with an angle of a line in the second group of one or more lines; and

determine the skew angle of the image based on the comparison of the first and second line angles if a difference between skew angles corresponding to each of the compared first and second line angles is lower than an error threshold.

2. The method as recited in claim 1, further comprising:

scanning a third region of the image for a third group of one or more lines if the difference between skew angles corresponding to each of the compared first and second line angles is higher than the error threshold; and

if none of the lines in the third group of one or more lines is reliable, using a processor to;

compare an angle of a line in the third group of one or more lines with the first and second line angles; and

determine the skew angle of the image based on the comparison of the first, second, and third line angles if a difference between skew angles corresponding to at least two of the compared first, second, and third line angles is lower than the error threshold.

3. The method as recited in claim 2, further comprising using a processor to:

determine the skew angle of the image based on a line in the first group of one or more lines if the line in the first group of one or more lines is reliable;

determine the skew angle of the image based on a line in the second group of one or more lines if the line in the second group of one or more lines is reliable;

determine the skew angle of the image based on a line in the third group of one or more lines if the line in the third group of one or more lines is reliable; and

determine that the skew angle is zero if the difference between skew angles corresponding to at least two of the compared first, second, and third line angles is higher than the error threshold.

4. The method as recited in claim 2, wherein the first region corresponds to an upper or lower portion of the image and the second and third regions each correspond to a lateral portion of the image.

5. The method as recited in claim 2, wherein reliability of a line found in at least one of the first, second, and third regions is dependent on at least one of:

a straightness of the found line;

a length of the found line; and

a length of a hole, if one exists, in the found line.

6. One or more computer-readable media having computer-executable instructions thereon which, when executed, implement a method for skew detection in an image, the method comprising:

scanning a first region of the image for a first group of one or more lines;

scanning a second region of the image for a second group of one or more lines if none of the lines in the first group of one or more lines is reliable; and

if none of the lines in the second group of one or more lines is reliable;

comparing an angle of a line in the first group of one or more lines with an angle of a line in the second group of one or more lines; and

determining the skew angle of the image based on the comparison of the first and second line angles if a difference between skew angles corresponding to each of the compared first and second line angles is lower than an error threshold.

7. An image processing device comprising:

a processor; and

the one or more computer-readable media as recited in claim 6, the computer-readable instructions thereon being configured to be executed by the processor.

8. The image processing device as recited in claim 7, wherein the image processing device comprises a printer, a scanner, a check scanner, a digital camera, a digital camcorder, or a portable photo viewer, or some combination thereof.