SYSTEM AND METHOD, AND COMPUTER PROGRAM PRODUCT FOR DETECTING AN EDGE IN SCAN DATA

• US 20100060910A1
• Filed: 09/08/2008
• Published: 03/11/2010
• Est. Priority Date: 09/08/2008
• Status: Active Grant

• Current Assignee: Tungsten Automation Corp.
• Original Assignee: Kofax Incorporated
• Inventors: Fechter, Joel S.
• Granted Patent: US 9,177,218 B2
• Time in Patent Office: Days
• US Class Current: 358/1.900
• CPC Class Codes: G06T 2207/10008 from scanner, fax or copier
• CPC Class Codes: G06T 2207/30176 Document
• CPC Class Codes: G06T 7/12 Edge-based segmentation
• CPC Class Codes: G06V 10/24 Aligning, centring, orientation detection or correction of the image
• CPC Class Codes: G06V 30/412 Layout analysis of documents structured with printed lines or input boxes, e.g. business forms or tables

Abstract

A system, method, and computer program product are provided for detecting an edge in scan data. In use, RGB scan data is analyzed for determining an approximate location of a background in the scan data representing a background adjacent a document having a similar color as the background. Additionally, a threshold is set for at least one of R, G and B, where the threshold is based in part on RGB values of the background and a predefined color threshold. Further, an intensity threshold is set. Further still, the scan data is analyzed using the thresholds for generating distribution points. Also, a first edge of the document is detected based on a location of a contour in the distribution points. In addition, the scan data and information about the detected edge are output.

Claims

1. A method for detecting an edge in scan data, comprising:

analyzing RGB scan data for determining an approximate location of a background in the scan data representing a background adjacent a document having a similar color as the background;

setting a threshold for at least one of R, G, and B, the threshold being based in part on RGB values of the background and a predefined color threshold;

setting an intensity threshold;

analyzing the scan data using the thresholds for generating distribution points;

detecting a first edge of the document based on a location of a contour in the distribution points; and

outputting the scan data and information about the detected edge.

2. The method of claim 1, wherein analyzing the RGB scan data for determining the approximate location of the background includes comparing RGB values to a background threshold value for a number of consecutive pixels, wherein if the RGB data of each of the consecutive pixels is below the background threshold value, the consecutive pixels are determined to be in the background.

3. The method of claim 1, wherein the intensity threshold is based in part on a background intensity and a predefined intensity threshold.

4. The method of claim 3, wherein the predefined intensity threshold is set below the predefined color threshold.

5. The method of claim 1, further comprising filtering out noise by analyzing sets of adjacent pixels of the scan data using the thresholds.

6. The method of claim 5, wherein the filtering uses a sliding window lookahead filter.

7. The method of claim 5, wherein the filtering includes analyzing the distribution points, wherein anomalies outside the contour are determined to be noise.

8. The method of claim 1, further comprising inverting a color of the document.

9. The method of claim 1, further comprising detecting a second edge of the document.

10. The method of claim 9, wherein the second edge of the document is found by analyzing the RGB scan data of the document.

11. The method of claim 9, wherein the second edge of the document is found by detecting the background adjacent the second edge of the document.

12. A method for detecting an edge in scan data, comprising:

analyzing RGB scan data for determining an approximate location of a background in the scan data representing a background adjacent a document having a similar color as the background;

setting a threshold for at least one of R, G, and B;

setting an intensity threshold, wherein the intensity threshold is set below a predefined color threshold;

analyzing the scan data using the thresholds for generating distribution points;

detecting a first edge of the document based on a location of a contour in the distribution points;

filtering out noise by analyzing sets of adjacent pixels of the scan data using the thresholds; and

outputting the scan data and information about the detected edge.

13. The method of claim 12, wherein analyzing the RGB scan data for determining the approximate location of the background includes comparing RGB values to background threshold value for a number of consecutive pixels, wherein if the RGB data of each of the consecutive pixels is below the background threshold value, the consecutive pixels are determined to be in the background.

14. The method of claim 12, wherein the filtering uses a sliding window lookahead filter.

15. The method of claim 12, wherein the filtering includes analyzing the distribution points, wherein anomalies outside the contour are determined to be noise.

16. The method of claim 12, further comprising inverting a color of the document.

17. The method of claim 12, further comprising detecting a second edge of the document.

18. The method of claim 17, wherein the second edge of the document is found by analyzing the RGB scan data of the document.

19. The method of claim 17, wherein the second edge of the document is found by detecting the background adjacent the second edge of the document.

20. The method of claim 12, wherein the threshold for the at least one of R, G and B is based in part on RGB values of the background and a predefined color threshold.