System and method for check fraud detection using signature validation

• US 7,249,717 B2
• Filed: 12/10/2004
• Issued: 07/31/2007
• Est. Priority Date: 12/10/2004
• Status: Active Grant

• Current Assignee: Mitek Systems Incorporated
• Original Assignee: Mitek Systems Incorporated
• Inventors: Nepomniachtchi, Grigori, Kotovich, Nikolay
• Primary Examiner(s): Lee; Michael G.
• Assistant Examiner(s): FRANKLIN, JAMARA ALZAIDA
• Application Number:
  US11/009,251
• Publication Number:
  US 20060124725A1
• Time in Patent Office: 963 Days
• Field of Search: 235/494, 235/487, 382/115, 382119-123
• US Class Current: 235/494
• 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: G06Q 20/24 Credit schemes, i.e. "pay after"
• CPC Class Codes: G06Q 20/3825 Use of electronic signatures
• CPC Class Codes: G06Q 20/389 Keeping log of transactions for guaranteeing non-repudiation of a transaction
• CPC Class Codes: G06Q 20/40 Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
• CPC Class Codes: G06Q 20/403 Solvency checks

Abstract

Systems and methods are provided for validating the authenticity of a signature on a document by providing a document from an account, the document including an actual signature and a machine-readable identifier, wherein the machine-readable identifier contains a string of data representing the integral characteristics of all valid account signatures and a person-specific confidence threshold. When the document is presented at a point of presentment, the document is scanned into a document-processing machine and the actual signature is compared against all valid account signatures.

Claims

1. A method of encoding a document with account signature data for signature validation, the method comprising the steps of:

compressing the account signature data to a fingerprint comprising machine-readable data corresponding to one or more account signatures, the fingerprint comprising a one-dimensional skeletonized version of account signature data containing 100 bytes of information or less;

evaluating the complexity and topology of each account signature;

encoding the fingerprint into a barcode;

printing the barcode on the document; and

determining a person-specific confidence threshold for each account signature based upon the complexity and topology of each account signature.

2. The method of claim 1, wherein the step of evaluating the complexity and topology of each account signature includes the step of determining the number of connected components in each signature.

3. The method of claim 2, further comprising the step of determining the number of holes in the components in each signature.

4. The method of claim 3, further comprising the steps of determining the size of each component and determining the size of each hole.

5. The method of claim 1, further comprising the step of building a one-dimensional skeleton of each account signature using a thinning algorithm.

6. The method of claim 5, wherein the step of building a one dimensional skeleton of each account signature using a thinning algorithm includes the step of determining the critical points of each account signature.

7. The method of claim 6, further comprising the step of building a list of all critical points, including positions and topological indices.

8. The method of claim 6, further comprising the step of building a description of every component as a list of critical points.

9. The method of claim 6, further comprising the step of adding a description of the path that connects the points inside the skeleton for each pair of adjacent critical points.