Method for applying a signature simplicity analysis for improving the accuracy of signature validation

• US 7,787,695 B2
• Filed: 06/06/2006
• Issued: 08/31/2010
• Est. Priority Date: 06/06/2006
• Status: Active Grant

• Current Assignee: Mitek Systems Incorporated
• Original Assignee: Mitek Systems Incorporated
• Inventors: Boutyline, Andrei, Nepomniachtchi, Grigori
• Primary Examiner(s): Ahmed; Samir A.
• Assistant Examiner(s): HU, FRED H.
• Application Number:
  US11/447,673
• Publication Number:
  US 20070280511A1
• Time in Patent Office: 1,547 Days
• Field of Search: None
• US Class Current: 382/186
• CPC Class Codes: G06V 30/1423 the instrument generating sequences of position coordinates corresponding to handwriting preprocessing or recognising digital ink G06V30/32
• CPC Class Codes: G06V 40/30 Writer recognition; Reading and verifying signatures

Abstract

The present invention provides a method for applying a signature simplicity analysis for improving the accuracy of signature validation, the method including the steps of generating a plurality of synthetic fraudulent signatures for a person, encoding authentic signatures of the person using signature simplicity and validating the signatures using signature simplicity.

Claims

1. A method for applying a signature simplicity analysis for improving the accuracy of signature validation, comprising the steps of:

using a computer system to generate a plurality of synthetic fraudulent signatures for a person;

encoding authentic signatures of the person using signature simplicity; and

validating the signatures using signature simplicity;

wherein the step of using a computer system to generate a plurality of synthetic fraudulent signatures for a person comprises the steps of;

inputting a name of the person;

inputting a set of simulation parameters;

performing a name mangling process to generate a set of various name versions based on the simulation parameter;

selecting a set of available fonts based on the simulation parameters;

selecting a set of available font characteristics based on the simulation parameters;

generating a set of initial signature images;

performing a name mangling process on all the initial signature images to create a plurality of intermediate signature images;

removing any image duplicates; and

outputting a set of unique synthetic signatures representing the person'"'"'s name.

2. The method of claim 1, wherein the name of the person is inputted in a form of First M. Last.

3. The method of claim 1, wherein the simulation parameters comprise font selection, font characteristics, name mangling and image mangling.

4. The method of claim 1, wherein:

the set of various name versions comprises ASCII data strings that represent name formats selected from the group consisting of;

F. Last;

Last;

First La; and

name synonyms.

5. The method of claim 1, wherein the step of generating a set of initial signature images comprises employing a Win32 SDK to generate a bitmap including the various name versions combined with the font selections.

6. A method for creating a set of unique synthetic signatures representing a person'"'"'s name, comprising the steps of:

inputting a name of a person and a set of simulation parameters;

using a computer system to perform a name mangling process to generate a set of various name versions based on the simulation parameter;

selecting a set of available fonts and font characteristics based on the simulation parameters;

generating a set of initial signature images;

performing the name mangling process on all the initial signature images to create a plurality of intermediate signature images; and

outputting a set of unique synthetic signatures representing the person'"'"'s name;

wherein the simulation parameters comprise font selection, font characteristics, name mangling and image mangling, and

the set of various name versions comprises ASCII data strings that represent name formats selected from the group consisting of;

F. Last;

Last;

First La; and

name synonyms.