Systems and methods for automatically detecting a corner in a digitally captured image

• US 6,985,631 B2
• Filed: 02/20/2002
• Issued: 01/10/2006
• Est. Priority Date: 02/20/2002
• Status: Active Grant

• Current Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Original Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Inventors: Zhang, Tong
• Primary Examiner(s): Johns, Andrew W.
• Assistant Examiner(s): Alavi, Amir
• Application Number:
  US10/079,663
• Publication Number:
  US 20030156201A1
• Time in Patent Office: 1,420 Days
• Field of Search: 382/168, 382/172, 382/173, 382/199, 382/237, 382/254, 382/266, 382/272, 382/275, 382/276, 358/462, 358/471, 358/488, 358/520, 358/522, 358/530
• US Class Current: 382/237
• CPC Class Codes: H04N 1/00681 Detecting the presence, position or size of a sheet or correcting its position before scanning H04N1/047 takes precedence; mode signalling H04N1/333; skew detection or correction in image signals H04N1/3878
• CPC Class Codes: H04N 1/00726 Other properties of the sheet, e.g. curvature or reflectivity
• CPC Class Codes: H04N 1/00737 using the scanning elements as detectors
• CPC Class Codes: H04N 1/00748 Detecting edges, e.g. of a stationary sheet
• CPC Class Codes: H04N 1/19594 using a television camera or a still video camera

Abstract

In one embodiment, the present invention is related to a method for processing a digitally captured image that comprises an imaged document. The method may comprise: transforming the digitally captured image into a binary image; searching the binary image to detect a plurality of edges of the imaged document; and analyzing the detected plurality of edges to determine at least one corner associated with the imaged document; wherein the transforming, searching, and analyzing are performed by programmable logic associated with a processor-based system.

Claims

1. A method for processing a digitally captured image that comprises an imaged document, said method comprising:

transforming said digitally captured image into a binary image, wherein a pixel of said binary image equals;

(1) a first logical value when a corresponding pixel in said digitally captured image is associated with a value greater than a luminance threshold;

or (2) a second logical value otherwise;

searching said binary image to detect a plurality of edges of said imaged document; and

analyzing said detected plurality of edges to determine at least one corner associated with said imaged document;

wherein said transforming, searching, and analyzing are performed by programmable logic associated with a processor-based system.

2. The method of claim 1 further comprising:

performing perspective adjustment utilizing said determined at least one corner.

3. The method of claim 1 wherein said first logical value is one and said second logical value is zero.

4. The method of claim 1 wherein said analyzing comprises:

analyzing a respective magnitude of slope associated with each of said plurality of edges.

5. The method of claim 1 wherein said analyzing comprises:

searching for a turning point in each of said plurality of edges.

6. The method of claim 5 wherein said analyzing comprises:

assigning detected turning points as ones of a plurality of corners.

7. The method of claim 1 wherein said analyzing comprises:

averaging locations associated with end points of ones of said plurality of edges to determine ones of a plurality of corners.

8. A system for processing a digitally captured image that comprises an imaged document, said system comprising:

means for transforming said digitally captured image into a binary image, wherein said means for transforming is operable to assign a first logical value to a pixel of said binary image that corresponds to a pixel of said digitally captured image that is associated with a value greater than a luminance threshold, and is operable to assign a second logical value otherwise;

means for detecting edges of said imaged document from said binary image; and

means for estimating at least one corner location of said imaged document from said detected edges.

9. The system of claim 8 further comprising:

means for performing perspective enhancement of said imaged document utilizing said at least one estimated corner location.

10. The system of claim 8 wherein said means for transforming is operable to calculate said luminance threshold of said digitally captured image.

11. The system of claim 10 wherein said means for transforming is operable to construct a histogram of luminance values of said digitally captured image to determine said luminance threshold.

12. The system of claim 8 wherein said means for estimating is operable to analyze said detected edges to identify turning points wherein said turning points are associated with a change in slope sign of said detected edges with respect to said binary image.

13. The system of claim 12 wherein said means for estimating utilizes detected turning points as corner locations.

14. The system of claim 8 wherein said system is selected from the group consisting of:

a personal computer, a personal digital assistant (PDA) and a digital camera.

15. A computer-readable medium comprising executable instructions for processing a digitally captured image that comprises an imaged document, said computer-readable medium comprising:

code for applying a luminance threshold to said digitally captured image to construct a binary image, wherein a pixel of said binary image equals;

(1) a first logical value when a corresponding pixel in said digitally captured image is associated with a value greater than said luminance threshold;

or (2) a second logical value otherwise;

code for detecting edges of said imaged document from said binary image, wherein said code for detecting is operable to search from each respective margin of said binary image for a change in value in said binary image to detect said edges; and

code for determining at least one corner location from said detected edges.

16. The computer-readable medium of claim 15 further comprising:

code for performing perspective enhancement of said imaged document utilizing said determined at least one corner location.

17. The computer-readable medium of claim 15 wherein said code for determining is operable to analyze said detected edges for points associated with a change in sign of slope with respect to said binary image.

18. The computer-readable medium of claim 17 wherein said points associated with a change in sign of slope are utilized as corner locations.