Association of finger pores and macrofeatures for identification of individuals

• US 6,591,002 B2
• Filed: 05/09/2002
• Issued: 07/08/2003
• Est. Priority Date: 07/29/1997
• Status: Expired due to Term

• Current Assignee: Open Invention Network LLC
• Original Assignee: Indivos Corporation (Solidus Networks Incorporated)
• Inventors: Lee, Jonathan Alexander, Lapsley, Philip Dean, Pare, Jr., David Ferrin
• Primary Examiner(s): AHMED, SAMIR ANWAR
• Application Number:
  US10/143,430
• Publication Number:
  US 20020154795A1
• Time in Patent Office: 425 Days
• Field of Search: 382/115, 382/124, 382/125, 283/68, 356/71, 235/380, 340/5.82, 340/5.83, 340/5.84
• US Class Current: 382/125
• CPC Class Codes: G06T 3/02 Affine transformations for image registration G06T3/147; for image mosaicing G06T3/4038
• CPC Class Codes: G06V 40/1353 Extracting features related to minutiae or pores
• CPC Class Codes: G06V 40/1371 Matching features related to minutiae or pores

Abstract

A method of identifying an individual from examination of their natural physical characteristics is shown. The method comprises obtaining from an individual during a registration process, a fingerprint image having at least one registration pore and at least one registration macrofeature; wherein registration pore data is derived from the registration pores, and registration macrofeature data is derived from the registration macrofeatures. In a bid step, a fingerprint image having at least one bid pore and at least one bid macrofeature is obtained; wherein bid pore data is derived from the bid pores and bid macrofeature data is derived from the bid macrofeatures. Bid associated data is constructed from associating the bid pore data with the bid macrofeature data, and constructing registration associated data derived from associating the registration pore data with the registration macrofeature data. The bid associated data is compared to the registration associated data to produce a correlation score where a successful or failed identification result is produced based on comparison of the correlation score to a predetermined threshold value.

Claims

1. In a computer-implemented credit card, ATM, or check cashing system, an anti-fraud fingerprint identification system that determines whether an object exhibits characteristics of a real human finger, comprising:

a fingerprint scanner;

means for determining a pore count from a fingerprint image obtained by the fingerprint scanner;

means for comparing a second pore count with the pore count;

means for determining registration pore data from registration pores from the fingerprint image, the fingerprint image including the registration pores and registration macrofeatures;

means for determining registration macrofeature data from the registration macrofeatures;

means for constructing a registration associated data derived from associating the registration pore data with the registration macrofeature data;

means for constructing the registration associated data includes means for associating a location for each registration pore and a registration fingerprint ridge on which the registration pore is located; and

wherein the registration fingerprint ridge is synthesized from a pair of valleys closest to the registration pore.

2. An anti-fraud fingerprint identification system according to claim 1, further comprising a database for storing fingerprints, each fingerprint including a pore count and associated with an individual.

3. An anti-fraud fingerprint identification system according to claim 1, further comprising:

means for comparing a registration associated data with a bid associated data derived from a bid fingerprint image to produce a correlation score; and

means for comparing the correlation score to a predetermined threshold value to arrive at a successful or failed identification result.

4. An anti-fraud fingerprint identification system according to claim 3, further comprising:

means for determining bid pore data from bid pores from the bid fingerprint image, the bid fingerprint image including the bid pores and bid macrofeatures;

means for determining bid macrofeature data from the bid macrofeatures; and

means for constructing the bid associated data derived from associating the bid pore data with the bid macrofeature data.

5. An anti-fraud fingerprint identification system comprising:

a fingerprint scanner;

means for determining a pore count from a fingerprint image obtained by to fingerprint scanner;

means for comparing a second-pore count with the pore count;

means for determining registration pore data from registration pores from the fingerprint image, the fingerprint image including to registration pores and registration macrofeatures;

means for determining registration macrofeature data from the registration macrofeatures; and

means for constructing a registration associated data derived from associating the registration pore data with the registration macrofeature data;

the means for constructing the registration associated data including means for associating a location for each registration pore and a registration fingerprint minutia point;

wherein to location of the registration pore is associated with a closest registration minutia point with which the registration pore shares ridge structure.

6. An anti-fraud fingerprint identification system according to claim 5, wherein the means for constructing the registration associated data includes means for associating a location for each registration pore and a registration fingerprint ridge on which the registration pore is located.

7. An anti-fraud fingerprint identification system according to claim 6, wherein the registration fingerprint ridge is synthesized from a pair of valleys closest to the registration pore.

8. An anti-fraud fingerprint identification system according to claim 6, further comprising means for assigning a macrofeature identification code to the registration fingerprint ridge.

9. An anti-fraud fingerprint identification system according to claim 5, wherein the location of the registration pore is associated with a linear displacement of the registration pore from the registration minutia point.

10. An anti-fraud fingerprint identification system according to claim 5, wherein the location of the registration pore is associated with an angle of displacement of the registration pore from the registration minutia point.