Method and system for searching form features for form identification

• US 20050196074A1
• Filed: 03/31/2005
• Published: 09/08/2005
• Est. Priority Date: 03/23/2000
• Status: Active Grant

• Current Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Original Assignee: Verity Incorporated (Healthstream Incorporated)
• Inventors: Deere, Emily Ann
• Granted Patent: US 7,421,126 B2
• Time in Patent Office: Days
• US Class Current: 382/305
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/1444 Selective acquisition, locating or processing of specific regions, e.g. highlighted text, fiducial marks or predetermined fields
• CPC Class Codes: Y10S 707/99936 Pattern matching access
• CPC Class Codes: Y10S 707/99937 Sorting

Abstract

A method of and system for identifying a target form for increased efficiency in an automated data capture process is described. Forms are scanned and stored as digitized images. Regions are defined on the form relative to corresponding reference points between the form and the digitized image. The regions are defined in areas that contain anticipated digitized data from data fields of the form. Digitized data is recognized through such means as optical character recognition (OCR) and the resulting string variable is compared in form to a plurality of formats expected for that data. Scoring systems are used to obtain a resultant score for a number of string variables which is compared to a predetermined confidence number. If said confidence number is reached, the form is flagged as a target form and used in the data capture process. A first step identification of certain graphical features can be added as an initial determination as to the source of the form.

Claims

1. A method of identifying a target form having a plurality of data fields, the method comprising:

storing a digitized image produced by a scanning device;

defining a region having boundaries in the digitized image;

recognizing a portion of the content of the digitized image located within the boundaries of the region;

associating the recognized content with a set of one or more characters;

comparing the format of the set of one or more characters to a plurality of format sequences; and

flagging the form for use in a data capture process if a comparison is found between the characters and one of the plurality of format sequences.

2. The method of claim 1, wherein the content of the digitized image located within the boundaries of the region is thickened prior to the recognition.

3. The method of claim 1, wherein recognizing the portion of the content is performed by recognition algorithms selected from the group comprising OCR, ICR and OMR.

4. The method of claim 1, wherein the scanning device is a dropout scanner.

5. The method of claim 1, wherein the digitized image includes a reference point corresponding to a point on the form, and the region is located relative to the reference point and corresponds with a predefined data field on the target form.

6. The method of claim 5, wherein the reference point corresponds with the top, left-hand comer of the form.

7. The method of claim 1, wherein the region is rectangular in shape.

8. The method of claim 1, wherein the set of one or more characters is compared to a list of predefined sets of one or more characters expected in the data field corresponding with the region and the comparison occurs when the set of one or more characters is substantially similar to one of the sets of one or more characters from the list of predefined sets of one or more characters.

9. The method of claim 1, wherein a computer program is used in the storing, defining, recognizing, associating, comparing and flagging acts.

10. A method of identifying a target form having a plurality of data fields, the method comprising:

storing a digitized image;

obtaining a set of one or more characters through recognition of the content located within boundaries of a region in the digitized image;

comparing the format of the set of one or more characters to a plurality of format sequences; and

flagging the form for use in a data capture process if a comparison is found between the set of one or more characters and one of the plurality of format sequences.

11. The method of claim 10, wherein the content of the digitized image located within the boundaries of the region is thickened prior to the recognition.

12. The method of claim 10, wherein the set of the one or more characters is obtained through recognition algorithms selected from the group comprising OCR, ICR and OMR.

13. The method of claim 10, wherein the digitized image includes a reference point corresponding to a point on the form, and the region is located relative to the reference point and corresponds with a predefined data field on the target form.

14. The method of claim 13, wherein the reference point corresponds with the top, left-hand comer of the form.

15. The method of claim 10, wherein the region is rectangular in shape.

16. The method of claim 10, wherein the set of one or more characters is compared to a list of predefined sets of one or more characters expected in the data field corresponding with the region and the comparison occurs when the set of one or more characters is substantially similar to one of the sets of one or more characters from the list of predefined sets of one or more characters.

17. The method of claim 10, wherein a computer program is used in the storing, obtaining, comparing and flagging acts.

18. A method of identifying a target form having a plurality of data fields, the method comprising:

(a) defining in a digitized image a region having boundaries;

(b) obtaining a set of one or more characters through recognition of the content located within boundaries of a region in the digitized image;

(c) comparing the format of the set of one or more characters to a plurality of format sequences;

(d) assigning a score based on a highest ranking comparison between the set of one or more characters and one of the plurality of format sequences;

(e) repeating acts (a) through (d) for at least one other region and adding the scores for the regions to get a total score; and

(f) comparing the total score to a confidence value whereby, if the total score equals or exceeds the confidence value, the form is identified as the target form intended for use in a data capture process.

19. The method of claim 18, wherein the digitized image is deleted when the total score does not equal or exceed the confidence value.

20. The method of claim 18, wherein the digitized image that does not attain a total score that equals or exceeds the confidence value is electronically attached to a target form which precedes the digitized image in the data capture process.

21. The method of claim 18, wherein the digitized image that does not attain a total score that equals or exceeds the confidence value is electronically attached to a target form which follows the digitized image in the data capture process.

22. The method of claim 18, wherein the content of the digitized image located within the boundaries of the region is thickened prior to the recognition.

23. The method of claim 18, wherein the digitized image includes a reference point corresponding to a point on the form and the region is located relative to the reference point and corresponds with a predefined data field on the target form.

24. The method of claim 23, wherein a computer program is used in the defining, obtaining, comparing, assigning, repeating and comparing acts.

25. The method of claim 24, wherein initial settings of the computer program which define the region can be adjusted through a configuration parameter to alter the location of the region relative to the reference point.

26. A system for identifying a target form having a plurality of data fields, the system comprising:

a recognition module configured to transform content of a digitized image located within boundaries of a region of the digitized image into a set of one or more characters, the region having boundaries;

an identification module configured to compare the format of the set of one or more characters to a plurality of format sequences; and

a scoring module configured to assign a score to the set of one or more characters, the score being based on a highest ranking comparison between the set of one or more characters and one of the plurality of format sequences, and to compare the score to a confidence value whereby, if the score exceeds the confidence value, the form is flagged as a target form for use in a data capture process.

27. The system of claim 26, wherein the scanning device is a dropout scanner.

28. The system of claim 26, wherein the recognition module uses a recognition algorithm selected from the group comprising OCR, ICR and OMR.

29. A system for identifying a target form having a plurality of data fields, the system comprising:

a recognition module configured to transform content located within boundaries of a region in a digitized image into a set of one or more characters;

an identification module configured to compare the format of the set of one or more characters to a plurality of format sequences; and

a scoring module configured to assign a score to the set of one or more characters, the score based on a highest ranking comparison between the set of one or more characters and one of the plurality of format sequences, and to compare the score to a confidence value whereby, if the score exceeds the confidence value, the form is flagged as a target form for use in a data capture process.

30. The system of claim 29, wherein the recognition module uses a recognition algorithm selected from the group comprising OCR, ICR and OMR.

31. A system for identifying a target form having a plurality of data fields, the system comprising:

a recognition module configured to transform content located within boundaries of a region in a digitized image into a set of one or more characters;

an identification module configured to compare the format of the set of one or more characters to a plurality of format sequences; and

a scoring module configured to identify the form for use in a data capture process if a comparison is found between the set of one or more characters and one of the plurality of format sequences.

32. The system of claim 31, wherein the recognition module uses a recognition algorithm selected from the group comprising OCR, ICR and OMR.

33. A method of identifying a target form having a plurality of data fields, the method comprising:

filtering possible candidate forms by use of graphical features;

comparing the format of recognized characters to a plurality of format sequences in a digitized image of one of the filtered candidate forms; and

flagging the one of the filtered candidate forms for use in a data capture process if a comparison is found between the recognized characters and one of the plurality of format sequences.

34. A computer usable medium having computer readable program code embodied therein for identifying a target form having a plurality of data fields, the computer readable code comprising instructions for:

storing a digitized image produced by a scanning device;

defining a region having boundaries in the digitized image;

recognizing a portion of the content of the digitized image located within the boundaries of the region;

associating the recognized content with a set of one or more characters;

comparing the format of the set of one or more characters to a plurality of format sequences; and

flagging the form for use in a data capture process if a comparison is found between the characters and one of the plurality of format sequences.

35. A programmable storage medium having computer readable program code embodied therein for identifying a~target form having a plurality of data fields, the computer readable code comprising instructions for:

storing a digitized image;

obtaining a set of one or more characters through recognition of the content located within boundaries of a region in the digitized image;

comparing the format of the set of one or more characters to a plurality of format sequences; and

flagging the form for use in a data capture process if a comparison is found between the set of one or more characters and one of the plurality. of format sequences.