Identification of a person based on ultra-sound scan analyses of hand bone geometry

• US 7,428,319 B2
• Filed: 08/04/2004
• Issued: 09/23/2008
• Est. Priority Date: 08/06/2003
• Status: Active Grant

• Current Assignee: Click-Into, Inc., John Ghorayeb, Volodymyr Tchouikevitch, Zinayida Bezvershenko
• Original Assignee: Alojz Muzar - Click Into Incorporated, John Ghorayeb, Volodymyr Tchouikevitch, Zinayida Bezvershenko
• Inventors: Bezvershenko, Zinayida, Tchouikevitch, Volodymyr, Ghorayeb, John
• Primary Examiner(s): Mariam; Daniel G
• Application Number:
  US10/910,303
• Publication Number:
  US 20050069177A1
• Time in Patent Office: 1,511 Days
• Field of Search: 382115-124, 382/128, 382/209, 382/218, 382/224, 382/254, 382/154, 340/5.1, 340/5.81, 340/5.82, 713/186
• US Class Current: 382/115
• CPC Class Codes: A61B 5/1075 for measuring dimensions by non-invasive methods, e.g. for determining thickness of tissue layer A61B8/0858 takes precedence
• CPC Class Codes: A61B 5/4504 Bones A61B5/4547 takes precedence
• CPC Class Codes: A61B 5/6825 Hand
• CPC Class Codes: A61B 8/0875 for diagnosis of bone A61B5/4504 takes precedence
• CPC Class Codes: A61B 8/483 involving the acquisition of a 3D volume of data
• CPC Class Codes: G01S 7/52036 using analysis of echo signal for target characterisation
• CPC Class Codes: G06F 18/00 Pattern recognition
• CPC Class Codes: G06V 40/10 Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
• CPC Class Codes: G06V 40/11 Hand-related biometrics; Hand pose recognition

Abstract

The invention disclosed provides a method of biometric identification of a person based on ultra-sound scan analyses of hand bones. For the purposes of identification/verification, a three dimensional (3D) ultra-sound scan of an individual'"'"'s hand bones is acquired to compare the scan with those stored in the record carrier that can be placed on the host or a remote computer.

Claims

1. A method for identifying a person based on ultrasound scan analysis of bone geometry of the person, the method comprising the steps of:

a) scanning a volumetric region of the person using ultrasound;

b) acquiring three-dimensional geometric data of the bone geometry of the volumetric region;

c) comparing the acquired three-dimensional geometric data previously stored geometric data to determine if a match exists.

2. The method as defined in claim 1 wherein the previously stored three-dimensional geometric data is retrieved by entering a personal identification number of the person.

3. The method as defined in claim 1, wherein the volumetric region comprises a plurality of bones, and before the comparing step c), the acquired data is restructured into separate bone entities corresponding to the bones in the volumetric region.

4. The method as defined in claim 3, wherein the acquired data comprises fewer bone entities than the previously stored data.

5. The method as defined in claim 3, wherein the volumetric region comprises a hand and the bone entities are categorized within different hand elements.

6. The method as defined in claim 3 further comprising the steps of:

i) defining a local coordinate system for each bone entity in relation to an absolute coordinate system of the volumetric region;

ii) transforming the acquired data for each bone entity from the absolute coordinate system to their respective local coordinate systems;

iii) determining relative locations of the bone entities based on a normalized template; and

iv) transforming the acquired data so as to move the bone entities to their relative locations.

7. The method as defined in claim 6, further comprising the step of redefining the acquired data to account for drift.

8. The method as defined in claim 6, further comprising the step of determining integral parameters of at least one of the bones to be used in the comparing step c).

9. The method as defined in claim 6, wherein the normalized template defines the geometry of a hand.

10. The method as defined in claim 1, wherein the volumetric region is placed on a scan platen prior to the scanning step a).

11. The method as defined in claim 10, wherein the volumetric region comprises a hand.

12. The method as defined in claim 1, wherein the acquired data comprises a combination of cross-sectional data within a plurality of planes extending through the volumetric region.

13. The method as defined in claim 12, wherein before the comparing step c), the acquired data is subjected to a noise reduction process and three-dimensional points representing the bone geometry are identified.

14. The method as defined in claim 1, further comprising the step of determining integral parameters of the bone geometry to be used in the comparing step c).

15. A method for identifying a person based on ultrasound scan analysis of bone geometry of a hand of the person, the method comprising the steps of:

a) scanning the hand of the person using ultrasound;

b) acquiring cross-sectional data within a plurality of planes extending through the hand;

c) subjecting the cross-sectional data to a noise reduction process and identifying points representing the bone geometry of the hand;

d) grouping the points into separate bone entities corresponding to bones in the hand;

e) defining a local coordinate system for each bone entity in relation to an absolute coordinate system of the hand;

f) transforming the points for each bone entity from the absolute coordinate system to their respective local coordinate systems;

g) determining relative locations of the bone entities based on a normalized template;

h) transforming the points so as to move the bone entities to their relative locations; and

i) comparing the to previously stored geometric data to determine if a match exists.

16. The method as defined in claim 15, wherein the hand is positioned in a predefined location prior to the scanning step a).

17. The method as defined in claim 15, wherein the stored geometric data is retrieved using a personal identification number of the person.

18. The method as defined in claim 15, wherein the comparing step i) comprises comparing integral parameters of the bone geometry, determined based on the points, with the stored geometric data.

19. A method for verifying a person'"'"'s identity based on ultrasound scan analysis of bone geometry of a hand of the person, the method comprising the steps of:

a) retrieving previously stored geometric data the hand of the person;

b) scanning the hand of the person using ultrasound;

c) acquiring three-dimensional geometric data of the bone geometry of the hand;

d) comparing the acquired three-dimensional geometric data to the previously stored geometric data to determine if a match exists.

20. The method as defined in claim 19, wherein before the comparing step d), the acquired data is restructured into separate bone entities and the bone entities are categorized within hand elements.

21. The method as defined in claim 20, further comprising the step of determining integral parameters of the bone geometry to be used in the comparing step c).

22. The method as defined in claim 20, wherein the previously stored three-dimensional geometric data is retrieved using a personal identification number of the person.

23. The method as defined in claim 22, wherein the stored geometric data is retrieved from a remote record carrier via wireless communication.

24. The method as defined in claim 19, wherein the volumetric region is placed on a scan platen prior to the scanning step b).