Granted Patent B2

US 9,785,627 · App. 14/162,179 · Granted Oct 10, 2017

Abstract

Claims (94)

1. A method of creating an electronic file corresponding to a printed artifact, the method comprising, by a processor:

receiving an image file of a printed form;

analyzing the image file to detect a potential form identifier on the printed form; and

automatically and without human intervention:

performing a search to identify an actual form that corresponds to the potential form identifier,

comparing the image file with the actual form to validate whether the image file is of a document page that corresponds to the actual form by:

using the actual form as a reference image,

overlaying a portion of the reference image on a corresponding portion of the image file to determine a validation value by using a polynomial matching model, and

determining whether the image file is of the document page that corresponds to the actual form by comparing the validation value against a threshold, and

upon validating that the image file is of the document page that corresponds to the actual form, locating a probable fill-in field on the document page, and mapping the probable fill-in field to an actual fill-in field of the actual form;

determining information to include in the probable fill-in field;

adding the information to the probable fill-field; and

saving the document page with the added information to a data file.

2. The method of claim 1 , further comprising, by the processor:

extracting information from the mapped fill-in field;

determining a label for the actual fill-in field; and

saving the extracted information in association with the label to the data file.

3. The method of claim 1 , further comprising, by the processor:

determining a label for the actual fill-in field; and

assigning the determined label to the probable fill-in field.

4. The method of claim 3 , further comprising, by the processor: using the label to retrieve the information to include in the probable fill-in field.

5. The method of claim 1 , further comprising, before the analyzing, processing the image file to enhance a quality of an image in the image file.

6. The method of claim 1 , wherein detecting the potential form identifier comprises performing one or more of the following:

analyzing the document to locate a character string of a predetermined format; or

analyzing the document to locate a character string that is in a position of a probable form identifier location.

7. The method of claim 1 , wherein validating whether the image file is of a document page that corresponds to the actual form comprises performing image subtraction using the actual form and the image file to measure a number of difference pixels and yield a validation value.

8. The method of claim 1 , wherein validating whether the image file is of a document page that corresponds to the actual form comprises:

performing image subtraction using the actual form and the image file to measure a number of difference pixels and yield a validation value; and

comparing the validation value against a threshold value.

9. The method of claim 1 , wherein the validating determines that the image file is not of a document that corresponds to the actual form, and the method further comprises:

analyzing the image file to detect a second potential form identifier on the printed form; and

automatically and without human intervention:

performing a search to identify a second actual form that corresponds to the potential form identifier, and

validating that the image file is of a document page that corresponds to the second actual form;

wherein the mapping comprises mapping the probable fill-in field to an actual fill-in field of the second actual form.

10. A mobile electronic device comprising:

an imaging device;

a processor; and

a computer-readable medium containing programming instructions that, when executed by the processor, cause the processor to:

receive an image file of a printed form;

analyze the image file to detect a potential form identifier on the document page;

automatically and without human intervention:

perform a search to identify an actual form that corresponds to the potential form identifier,

compare the image file with the actual form to validate whether the image file is of a document page that corresponds to the actual form by:

using the actual form as a reference image,

overlaying a portion of the reference image on a corresponding portion of the image file to determine a validation value by using a polynomial matching model, and determining whether the image file is of the document page that corresponds to the actual form by comparing the validation value against a threshold,

locate a probable fill-in field on the document page, and

map the probable fill-in field to an actual fill-in field of the actual form;

determine information to include in the probable fill-in field;

add the information to the probable fill-in field; and

save the document page with the added information to a data file.

11. The device of claim 10 , further comprising additional programming instructions that, when executed, cause the processor to:

extract information from the mapped fill-in field;

determine a label for the actual fill-in field; and

save the extracted information in association with the label to the data file.

12. The device of claim 10 , further comprising additional programming instructions that, when executed, cause the processor to:

determine a label for the actual fill-in field; and

assign the determined label to the probable fill-in field.

13. The device of claim 12 , further comprising additional programming instructions that, when executed, cause the processor to:

use the label to retrieve the information to include in the probable fill-in field.

14. The device of claim 10 , further comprising additional programming instructions that, when executed, cause the processor to process the image file to enhance a quality of an image in the image file before detecting the potential form identifier.

15. The device of claim 10 , wherein the instructions to analyze the image file to detect the potential form identifier comprise instructions to perform one or more of the following:

analyze the document to locate a character string of a predetermined format; or

analyze the document to locate a character string that is in a position of a probable form identifier location.

16. The device of claim 10 , wherein the instructions to validate that the image file is of a document page that corresponds to the actual form comprise instructions to perform image subtraction using the actual form and the image file to measure a number of difference pixels and yield a validation value.

17. The device of claim 11 , wherein the instructions to validate that the image file is of a document page that corresponds to the actual form comprise instructions that, when executed, cause the processor to:

perform image subtraction using the actual form and the image file to measure a number of difference pixels and yield a validation value; and

compare the validation value against a threshold value.

18. The device of claim 10 , further comprising additional programming instructions that, when executed, cause the processor to, if the validating determines that the image file is not of a document that corresponds to the actual form:

analyze the image file to detect a second potential form identifier on the printed form;

automatically and without human intervention:

perform a search to identify a second actual form that corresponds to the potential form identifier, and

validate that the image file is of a document page that corresponds to the second actual form; and

when mapping the probable fill-in field to an actual fill-in field, use an actual fill-in field of the second actual form.

19. A method of creating an electronic file corresponding to a printed artifact, the method comprising, by a processor:

receiving an image file of a printed form;

processing the image file to enhance a quality of an image in the image file;

analyzing the image file to detect a potential form identifier on the printed form, wherein the potential form identifier comprises at least a portion of a title or a form catalogue page number that uniquely identifies a form;

automatically and without human intervention:

performing a search to identify an actual form that corresponds to the potential form identifier;

validating whether the image file is of a document page that corresponds to the actual form polynomial matching model, wherein validating further comprises:

using the actual form as a reference image,

overlaying a portion of the reference image on a corresponding portion of the image file to determine a validation value,

determining whether the image file is of the document page that corresponds to the actual form by comparing the validation value against a threshold, wherein the threshold is based on one or more coefficients of the polynomial matching model; and

upon validating that the image file is of a document page that corresponds to the actual form, locating a probable fill-in field on the document page, and mapping the probable fill-in field to an actual fill-in field of the actual form;

determining information to include in the probable fill-in field;

adding the information to the probable fill-in field; and

saving the document page with the added information to a data file.

20. The method of claim 19 , further comprising, by the processor:

determining a label for the actual fill-in field;

assigning the determined label to the probable fill-in field;

using the label to retrieve the information to include in the probable fill-in field.

21. The method of claim 1 , wherein the threshold against which the validation value is compared is based on one or more coefficients of the polynomial matching model.

22. The device of claim 10 , wherein the threshold against which the validation value is compared is based on one or more coefficients of the polynomial matching model.

Assignments (10)