System and method of determining image skew using connected components

• US 20050238252A1
• Filed: 04/26/2004
• Published: 10/27/2005
• Est. Priority Date: 04/26/2004
• Status: Active Grant

• Current Assignee: Truist Bank (Private Banking) (Truist Financial Corp.)
• Original Assignee: International Business Machines Corporation
• Inventors: Sathe, Madhura, Prakash, Ravinder
• Granted Patent: US 7,336,813 B2
• Time in Patent Office: Days
• US Class Current: 382/289
• CPC Class Codes: G06T 2207/10008 from scanner, fax or copier
• CPC Class Codes: G06T 2207/30176 Document
• CPC Class Codes: G06T 7/11 Region-based segmentation
• CPC Class Codes: G06T 7/73 using feature-based methods
• CPC Class Codes: G06V 30/1478 of characters or characters lines
• CPC Class Codes: G06V 30/2253 Recognition of characters printed with magnetic ink G06V30/2247 takes precedence

Abstract

A system and method for determining skew of a document image. An image processing system is provided, comprising: an image segmentation system that identifies and segments a line of printed characters; and a skew processing system that determines the skew by calculating slope values for pairs of characters in the line.

Claims

1. An image processing system for determining a skew of a document image, comprising:

an image segmentation system that identifies and segments a line of printed characters; and

a skew processing system that determines the skew by calculating slope values for pairs of characters in the line.

2. The image processing system of claim 1, wherein each pair of characters comprises a first and a second character printed adjacent to each other.

3. The image processing system of claim 1, wherein the skew is further determined based on a median slope value calculated from each of the pairs of characters in the line.

4. The image processing system of claim 1, wherein the slope value for each pair of characters is calculated based on a position of a lower right coordinate of each character in the pair.

5. The image processing system of claim 1, wherein the image segmentation system identifies and segments the line of printed characters by identifying connected components that reside in a predetermined region of the document image.

6. The image processing system of claim 5, wherein the image segmentation system identifies and segments the line of printed characters by identifying connected components that meet predetermined size criteria.

7. The image processing system of claim 1, wherein the document image comprises a black white image.

8. The image processing system of claim 1, wherein the line of printed characters comprises a magnetic ink character recognition (MICR) code line.

9. A method for determining a skew of a document image, comprising:

identifying and segmenting a line of printed characters on the document image; and

determining the skew of the document image by calculating slope values for pairs of characters in the line.

10. The method of claim 9, wherein each pair of characters comprises a first and a second character printed adjacent to each other.

11. The method of claim 9, wherein the skew is further determined based on a median slope value calculated for each of the pairs of characters in the line.

12. The method of claim 9, wherein the slope for each pair of characters is calculated based on a position of a lower right coordinate of each character in the pair.

13. The method of claim 9, wherein the step of identifying and segmenting the line of printed characters includes the step of identifying connected components that reside in a predetermined region of the document image.

14. The method of claim 13, wherein the step of identifying and segmenting the line of printed characters includes the further step of identifying connected components that meet predetermined size criteria.

15. The method of claim 9, wherein the document image comprises a black white image.

16. The method of claim 9, wherein the line of printed characters comprises a magnetic ink character recognition (MICR) code line.

17. A program product stored on a recordable medium for determining a skew of a document image, comprising:

means for identifying and segmenting a line of printed characters on the document image; and

means for determining the skew of the document image by calculating slope values for pairs of characters in the line.

18. The program product of claim 17, wherein each pair of characters comprises a first and a second character printed adjacent to each other.

19. The program product of claim 17, wherein the skew is further determined based on a median slope value calculated for each of the pairs of characters in the line.

20. The program product of claim 17, wherein the slope for each pair of characters is calculated based on a position of a lower right coordinate of each character in the pair.

21. The program product of claim 17, wherein the means for identifying and segmenting the line of printed characters includes means for identifying connected components that reside in a predetermined region of the document image.

22. The program product of claim 21, wherein the means for identifying and segmenting the line of printed characters includes means for identifying connected components that meet predetermined size criteria.

23. The program product of claim 17, wherein the document image comprises a black white image.

24. The program product of claim 17, wherein the line of printed characters comprises a magnetic ink character recognition (MICR) code line.

25. An image processing system for determining a skew of a document image, comprising:

a system for inputting a segmented set of printed characters;

a system that calculates slope values for pairs of characters in the set; and

a system that identifies a medium slope value among all the calculated slope values.

26. The image processing system of claim 25, wherein the segmented set of printed characters comprises a magnetic ink character recognition (MICR) code line.

27. The image processing system of claim 25, wherein each character pair comprises adjacent characters.

28. The image processing system of claim 25, wherein the slope for each pair of characters is calculated based on a position of a lower right coordinate of each character in the pair.