METHOD AND SYSTEM FOR SKEW DETECTION OF A SCANNED DOCUMENT USING CONNECTED COMPONENTS ANALYSIS

• US 20100195933A1
• Filed: 01/30/2009
• Published: 08/05/2010
• Est. Priority Date: 01/30/2009
• Status: Active Grant

• Current Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Original Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Inventors: Nafarieh, Asghar
• Granted Patent: US 8,290,302 B2
• Time in Patent Office: Days
• US Class Current: 382/289
• CPC Class Codes: G06V 10/243 by compensating for image skew or non-uniform image deformations

Abstract

A method and system for skew detection is provided using connected components analysis. The methodology includes extracting connected components corresponding to the image and analyzing the image based on said connected components for determining skew of the image

Claims

1. In a computer system, a method for detecting skew of an image using connected components analysis performed by at least one processor, the method comprising:

extracting connected components corresponding to said image;

analyzing said image based on said connected components;

identifying blobs based on pixel connectivity and determining the boundary points;

sorting the at least one identified group of pixels based on its location on the image;

grouping the blobs into data sets based on their location on the image; and

determining a skew angle of said image using at least one data set.

2. The method according to claim 1, further comprising varying the skew angle based upon user preferences.

3. The method according to claim 1, further comprising scanning a document for obtaining said image.

4. The method according to claim 1, further comprising rotating the image to a desired position based on the determined skew angle.

5. The method according to claim 1, further comprising determining the population count for each of said blobs.

6. The method according to claim 1, wherein the boundary points consist of (x, y, width, height), where x, y are coordinates of the upper left-hand corner of a bounding box.

7. The method according to claim 1, wherein each of said plurality of data sets consists of blobs of said image.

8. The method according to claim 1, further comprising scanning a plurality of images and determining one of the plurality of images to be a reference image.

9. The method according to claim 1, wherein the step of sorting of the at least one identified group of blobs is based on blob locations from left to right and top to bottom.

10. The method according to claim 1, wherein an image signal representing a first blob of said image is identified as falling within a first bounding box, and an image signal representing a second blob of said image is identified as falling within a second bounding box.

11. A system for skew detection of an image comprising:

at least one computing device having at least one processor;

a blob identifying module for identifying connected components within said image using connected components analysis; and

a skew detection module for computing skew angle of said image using said identified connected components, each of said modules having a set of programmable instructions configured for execution by said at least one processor.

12. The system according to claim 11, wherein at least one computing device is a server in operative communication with a plurality of devices each having a scanning assembly for scanning documents.

13. The system according to claim 11, further comprising means for rotating the image based on said computed skew angle.

14. The system according to claim 11, wherein the blob identifying module comprises means for extracting one or more connected components of said image.

15. The system according to claim 11, wherein the skew detection module comprises means for computing the skew angle of said image by using coordinates of at least one group of blobs.

16. A computer-readable medium storing programmable instructions configured for execution by at least one processor for performing a method comprising:

extracting connected components corresponding to said image;

analyzing said image based on said connected components;

identifying blobs based on pixel connectivity and determining the boundary points;

sorting the at least one identified group of pixels based on its location on the image;

grouping the blobs into data sets based on their location on the image; and

determining a skew angle of said image using at least one data set.

17. The computer-readable medium according to claim 16, further comprising the step of rotating the image to a desired position based on said determined skew angle.

18. The computer-readable medium according to claim 16, wherein the step of sorting of the at least one identified group of blobs is based on blob locations from left to right and top to bottom.

19. The computer-readable medium according to claim 16, wherein an image signal representing a first blob of said image is identified as falling within a first bounding box, and an image signal representing a second blob of said image is identified as falling within a second bounding box.

20. A method for skew detection of an image comprising:

identifying connected components within said image using connected components analysis; and

computing skew angle of said image using said identified connected components.

21. The method according to claim 20, further comprising rotating the image based on said computed skew angle.