Financial transaction processing systems and methods

• US 6,097,834 A
• Filed: 06/13/1997
• Issued: 08/01/2000
• Est. Priority Date: 06/13/1997
• Status: Expired due to Fees

• Current Assignee: Paystation America, Inc.
• Original Assignee: Paystation America, Inc.
• Inventors: Strovink, Eric F., Krouse, Louis J.
• Primary Examiner(s): BELLA, MATTHEW C
• Application Number:
  US08/874,312
• Time in Patent Office: 1,145 Days
• Field of Search: 382/137, 382/176, 382/306, 382/135, 382/139, 382/138, 705/44, 705/45, 707/522, 707/52, 707/6
• US Class Current: 382/137
• CPC Class Codes: G06Q 20/04 Payment circuits
• CPC Class Codes: G06Q 20/042 characterized in that the payment protocol involves at least one cheque
• CPC Class Codes: G07D 7/12 Visible light, infrared or ultraviolet radiation

Abstract

In accordance with the present invention, financial transaction processing systems and methods are provided. One preferred embodiment of a method according to one aspect of the present invention includes generating an optically scanned image of at least a portion of document containing visual data, in a particular format, representing information related to the financial transaction. Recognition characteristics are generated from the scanned image and are compared to respective sets of reference recognition characteristics generated from respective other transaction documents having different respective formats to determine therefrom whether the particular format of the visual data matches one of the respective formats of the other documents. When such a match is found to exist, location is determined of a field in the scanned image to which optical character recognition may be applied to generate therefrom the information, based upon the respective format found to match the particular format of the visual data. Optical character recognition is then utilized to generate said visual data from said location.

Claims

1. A system for use in processing a financial transaction based at least in part upon visual data representing information related to said transaction and formed on a document having a particular format, said system comprising:

a. an optical scanner for generating a scanned image of at least a portion of said document containing said visual representation;

b. an image characterization generator for generating recognition characteristics from said scanned image;

c. a recognition characteristic comparator for comparing said recognition characteristics to respective sets of reference recognition characteristics generated from respective other transaction documents having different respective formats and for determining therefrom whether said particular format matches one of the respective formats of said other documents;

d. a field location generator for determining, based upon the one respective format when the particular format is determined to match said one respective format, location of a field in said scanned image to which optical character recognition is applied to generate therefrom said information; and

e. an image processor for utilizing optical character recognition to generate said visual data from said location.

2. A system according to claim 1, wherein said characterization generator includes an image de-skewer for registering the scanned image with respect to a coordinate system.

3. A system according to claim 2, wherein said image de-skewer registers said scanned image by registering dark pixels closest to respective adjacent edges of said scanned image with respect to said coordinate system.

4. A system according to claim 1, wherein said characterization generator comprises a noise eliminator for eliminating noise in said scanned image by replacing dark portions of fewer than 3 pixels in said scanned image with whitespace.

5. A system according to claim 4, wherein said characterization generator also comprises an image enhancer for enhancing said scanned image by replacing whitespace, extending in two mutually orthogonal directions around each dark pixel remaining after elimination of said noise, with respective predetermined numbers of dark pixels in each of said directions.

6. A system according to claim 1, wherein said characterization generator comprises a dark pixel group locator for locating groups of dark pixels whose sizes exceeds a predetermined threshold.

7. A system according to claim 6, wherein said recognition characteristics comprise locations of said groups of dark pixels located by said dark pixel group locator, and said respective sets of reference recognition characteristics comprise respective sets of locations of groups of dark pixels from respective scanned images of said respective other transaction documents.

8. A system according to claim 1, wherein said information comprises an amount payable from a customer, and said visual representation comprises an amount due represented numerically and an account number of said customer.

9. A method for use in processing a financial transaction based at least in part upon visual data representing information related to said transaction and formed on a document having a particular format, said method comprising:

a. generating an optically scanned image of at least a portion of said document containing said visual representation;

b. generating recognition characteristics from said scanned image;

c. comparing said recognition characteristics to respective sets of reference recognition characteristics generated from respective other transaction documents having different respective formats and determining therefrom whether said particular format matches one of the respective formats of said other documents;

d. determining, based upon the one respective format when the particular format is determined to match said one respective format, location of a field in said scanned image to which optical character recognition is applied to generate therefrom said information; and

e. utilizing optical character recognition to generate said visual data from said location.

10. A method according to claim 9, further comprising eliminating noise in said scanned image, prior to comparison step (c), by replacing dark portions of fewer than 3 pixels in said scanned image with whitespace.

11. A method according to claim 10, further comprising enhancing said scanned image by replacing whitespace, extending in two mutually orthogonal directions around each dark pixel remaining after elimination of said noise, with respective predetermined numbers of dark pixels in each of said directions.

12. A method according to claim 9, further comprising locating groups of dark pixels whose sizes exceed a predetermined threshold.

13. A system according to claim 9, wherein said recognition characteristics comprise locations of groups of dark pixels whose sizes exceed a predetermined threshold, and said respective sets of reference recognition characteristics comprise respective sets of locations of groups of dark pixels from respective scanned images of said respective other transaction documents.

14. A system according to claim 9, wherein said information comprises an amount payable from a customer, and said visual representation comprises an amount due represented numerically and an account number of said customer.