Resolving character data boundaries

• US 7,362,902 B1
• Filed: 05/28/2004
• Issued: 04/22/2008
• Est. Priority Date: 05/28/2004
• Status: Active Grant

• Current Assignee: Conduent Business Services, LLC (Conduent, Inc.)
• Original Assignee: Xerox Business Services, LLC (Conduent, Inc.)
• Inventors: Smith, Gary S., Baker, Billy S.
• Primary Examiner(s): Ahmed; Samir
• Assistant Examiner(s): CUNNINGHAM, GREGORY F
• Application Number:
  US10/856,311
• Time in Patent Office: 1,425 Days
• Field of Search: 382/182, 382/187, 382/321, 382/229, 434/159, 706/20, 725/19
• US Class Current: 382/229
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/1452 based on positionally close symbols, e.g. amount sign or URL-specific characters

Abstract

Character data for a plurality of characters on which character recognition is being performed is received for processing. The character data includes character assignments and character locations. A reference location is defined in relation to a location of one of the characters, and the character assignments are resolved into one or more groupings according to a distance of the characters from the reference location.

Claims

1. A method of resolving character assignments into groupings of characters, comprising:

receiving character data for a plurality of characters on which character recognition is being performed, the character data including character assignments representing characters determined by character recognition and locations of characters;

defining a reference location in relation to a location of one of the characters; and

resolving the character assignments into one or more groupings of characters according to a distance of the characters from the reference location.

2. The method of claim 1 further comprising:

checking the contents of at least one grouping by comparing one or more character assignments resolved into the grouping against at least one specified characteristic of the grouping.

3. The method of claim 2 wherein the specified characteristic is at least one of a number of characters, a location of spaces or lack of spaces between characters, a type of characters, or a specified set of characters.

4. The method of claim 2 further comprising transferring one or more character assignments from the grouping to an adjacent grouping if the character assignments resolved into the grouping are inconsistent with the at least one specified characteristic of the grouping.

5. The method of claim 4 further comprising re-checking the contents of at least one of the groupings or the adjacent groupings.

6. The method of claim 1 wherein the reference location is defined in relation to a location of an end most character.

7. The method of claim 1 wherein the plurality of characters on which character recognition is being performed are arranged in a plurality of lines;

and

wherein receiving character data for a plurality of characters comprises receiving character data for a plurality of characters residing in a common line of characters.

8. The method of claim 7 further comprising defining a coordinate axis substantially perpendicular to the plurality of lines of characters;

and

wherein receiving character data for a plurality of characters residing in a common line of characters comprises receiving character data for a plurality of characters residing in a specified range of coordinates on the coordinate axis.

9. The method of claim 1 wherein resolving the character assignments into one or more groupings according to their distance from the reference location comprises:

defining a plurality of grouping boundaries in relation to the reference location; and

resolving character assignments into groupings according to the grouping boundaries.

10. The method of claim 9 wherein characters on which character recognition is being performed reside on an image having one or more fields defined thereon;

and

wherein at least one dimension between adjacent grouping boundaries corresponds to a dimension of a field.

11. The method of claim 1 further comprising:

recognizing characters on an image in a plurality of read zones, at least two of the read zones overlapping; and

checking for characters assignments duplicated in the at least two read zones.

12. The method of claim 11 further comprising resolving duplicated character assignments into a grouping according to at least one of a specified characteristic of one or more groupings or a distance from the reference location.

13. An article comprising a machine-readable medium storing instructions adapted to cause one or more machines to perform operations comprising:

receiving character data for a plurality of characters on which character recognition is being performed, the character data including character assignments representing characters determined by character recognition and locations of characters;

defining a reference location in relation to a location of one of the characters; and

resolving the character assignments into one or more groupings of characters according to a distance of the characters from the reference location.

14. The article of claim 13 wherein the instructions are further adapted to cause one or machines to perform operations comprising:

checking the contents of at least one grouping by comparing one or more character assignments resolved into the grouping against at least one specified characteristic of the grouping.

15. The article of claim 14 wherein the specified characteristic is at least one of number of characters, a location of spaces or lack of spaces between characters, a type of characters, or a specified set of characters.

16. The article of claim 14 wherein the instructions are further adapted to cause one or machines to perform operations comprising:

transferring one or more character assignments from the grouping to an adjacent grouping if the character assignments resolved into the grouping are inconsistent with the at least one specified characteristic of the grouping.

17. The article of claim 16 wherein the instructions are further adapted to cause one or machines to perform operations comprising re-checking the contents of at least one of the groupings or the adjacent groupings.

18. The article of claim 13 wherein the reference location is defined in relation to a location of an end most character.

19. The article of claim 13 wherein the plurality of characters on which character recognition is being performed are arranged in a plurality of lines;

and

wherein receiving character data for a plurality of characters comprises receiving character data for a plurality of characters residing in a common line of characters.

20. The article of claim 19 wherein the instructions are further adapted to cause one or machines to perform operations comprising defining a coordinate axis substantially perpendicular to the plurality of lines of characters;

and

wherein receiving character data for a plurality of characters residing in a common line of characters comprises receiving character data for a plurality of characters residing in a specified range of coordinates on the coordinate axis.

21. The article of claim 13 wherein resolving the character assignments into one or more groupings according to their distance from the reference location comprises:

defining a plurality of grouping boundaries in relation to the reference location; and

resolving character assignments into groupings according to the grouping boundaries.

22. The article of claim 21 wherein characters on which character recognition is being performed reside on an image having one or more fields defined thereon;

and

wherein at least one dimension between adjacent grouping boundaries corresponds to a dimension of a field.

23. The article of claim 13 wherein the instructions are further adapted to cause one or machines to perform operations comprising:

recognizing characters on an image in a plurality of read zones, at least two of the read zones overlapping; and

checking for characters assignments duplicated in the at least two read zones.

24. The article of claim 23 wherein the instructions are further adapted to cause one or machines to perform operations comprising resolving duplicated character assignments into a grouping according to at least one of a specified characteristic of one or more groupings or a distance from the reference location.

25. A system for resolving character assignments into groupings of characters including a processor configured to perform operations comprising:

receiving character data for a plurality of characters on which character recognition is being performed, the character data including character assignments representing characters determined by character recognition and locations of characters;

defining a reference location in relation to a location of one of the characters; and

resolving the character assignments into one or more groupings of characters according to a distance of the characters from the reference location.

26. The system of claim 25 wherein the processor is further configured to perform operations comprising:

checking the contents of at least one grouping by comparing one or more character assignments resolved into the grouping against at least one specified characteristic of the grouping.

27. The system of claim 26 wherein the specified characteristic is at least one of number of characters, a location of spaces or lack of spaces between characters, a type of characters, or a specified set of characters.

28. The system of claim 26 wherein the processor is further configured to perform operations comprising transferring one or more character assignments from the grouping to an adjacent grouping if the character assignments resolved into the grouping are inconsistent with the at least one specified characteristic of the grouping.

29. The system of claim 28 wherein the processor is further configured to perform operations comprising re-checking the contents of at least one of the groupings or the adjacent groupings.

30. The system of claim 25 wherein the reference location is defined in relation to a location of an end most character.

31. The system of claim 25 wherein the plurality of characters on which character recognition is being performed are arranged in a plurality of lines;

and

wherein receiving character data for a plurality of characters comprises receiving character data for a plurality of characters residing in a common line of characters.

32. The system of claim 31 wherein the processor is further configured to perform operations comprising defining a coordinate axis substantially perpendicular to the plurality of lines of characters;

and

wherein receiving character data for a plurality of characters residing in a common line of characters comprises receiving character data for a plurality of characters residing in a specified range of coordinates on the coordinate axis.

33. The system of claim 25 wherein resolving the character assignments into one or more groupings according to their distance from the reference location comprises:

defining a plurality of grouping boundaries in relation to the reference location; and

resolving character assignments into groupings according to the grouping boundaries.

34. The system of claim 33 wherein characters on which character recognition is being performed reside on an image having one or more fields defined thereon;

and

wherein at least one dimension between adjacent grouping boundaries corresponds to a dimension of a field.

35. The system of claim 25 wherein the processor is further configured to perform operations comprising:

recognizing characters on an image in a plurality of read zones, at least two of the read zones overlapping; and

checking for characters assignments duplicated in the at least two read zones.

36. The system of claim 35 wherein the processor is further configured to perform operations comprising resolving duplicated character assignments into a grouping according to at least one of a specified characteristic of one or more groupings or a distance from the reference location.