SYSTEM AND METHOD FOR EXTRACTING TWO-DIMENSIONAL FINGERPRINTS FROM HIGH RESOLUTION THREE-DIMENSIONAL SURFACE DATA OBTAINED FROM CONTACTLESS, STAND-OFF SENSORS

• US 20160180142A1
• Filed: 12/17/2014
• Published: 06/23/2016
• Est. Priority Date: 12/17/2014
• Status: Active Grant

• Current Assignee: Peraton, Inc.
• Original Assignee: Northrop Grumman Systems Corporation (Northrop Grumman Corporation)
• Inventors: Riddle, Jack G., Brucks, Timothy M., Becker, Michael M.
• Granted Patent: US 9,734,381 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06V 10/993 Evaluation of the quality of the acquired pattern
• CPC Class Codes: G06V 20/64 Three-dimensional objects
• CPC Class Codes: G06V 40/107 Static hand or arm
• CPC Class Codes: G06V 40/1312 direct reading, e.g. contactless acquisition
• CPC Class Codes: G06V 40/1359 Extracting features related to ridge properties; Determining the fingerprint type, e.g. whorl or loop

Abstract

Disclosed herein are systems and methods for extracting two-dimensional fingerprints from high resolution three-dimensional surface data obtained from contactless, stand-off sensors. The system may include a three-dimensional sensor that generates three-dimensional surface data of a hand and one or more fingers of a subject and a processor, coupled to the three-dimensional sensor, and a memory associated with the processor, in which the processor executes instructions stored in the memory collect three-dimensional surface data of the subject hand and one or more subject fingers generated by the three-dimensional sensor, estimate a hand pose of the subject based on the collected three-dimensional surface data, unroll one or more two-dimensional fingerprints from the extracted fingerprint information, determine a fingerprint quality score for each of the one or more two-dimensional fingerprints and for each of the one or more two-dimensional fingerprints that have a sufficiently high determined fingerprint quality score, store the two-dimensional fingerprint.

Claims

1. A system for extracting two-dimensional fingerprints from high resolution three-dimensional surface data obtained from contactless, stand-off sensors, comprising:

a three-dimensional sensor that generates three-dimensional surface data of a hand and one or more fingers of a subject;

a processor, coupled to the three-dimensional sensor, and a memory associated with the processor, wherein the processor executes instructions stored in the memory to extract two-dimensional fingerprints from high resolution three-dimensional surface data by;

collecting three-dimensional surface data of the subject hand and one or more subject fingers generated by the three-dimensional sensor;

estimating a hand pose of the subject based on the collected three-dimensional surface data;

based on the estimated hand pose, extracting fingerprint information from the collected three-dimensional surface data;

unrolling one or more two-dimensional fingerprints from the extracted fingerprint information;

determining a fingerprint quality score for each of the one or more two-dimensional fingerprints; and

for each of the one or more two-dimensional fingerprints that have a sufficiently high determined fingerprint quality score, storing the two-dimensional fingerprint.

2. The system of claim 1 wherein the three-dimensional sensor is a contactless, stand-off sensor in which the three-dimensional sensor generates the three-dimensional surface data without contacting the subject fingers.

3. The system of claim 1 wherein the three-dimensional sensor is a Photon-X sensor.

4. The system of claim 1 wherein the three-dimensional sensor generates three-dimensional surface data that includes a dense set of surface points, wherein each point samples a three-dimensional position as well as other attributes of the one or more subject fingers including surface normal information and color.

5. The system of claim 4 wherein the collecting three-dimensional surface data includes generating a triangulated, three-dimensional surface mesh from the dense surface point set.

6. The system of claim 5 wherein the triangulated, three-dimensional surface mesh includes a plurality of point vertices and triangular facets that provides a description of the surface geometry with sufficient resolution to distinguish depth differences between ridges and valleys on a fingertip.

7. The system of claim 5 wherein the estimating a hand pose of the subject includes:

extracting a three-dimensional contour of the subject hand from the triangulated, three-dimensional surface mesh; and

performing a set of initial hand pose tests.

8. The system of claim 7 wherein the performing a set of initial hand pose tests includes:

locating the hand thumb in the three-dimensional contour;

verifying that the hand palm is facing towards the three-dimensional sensor;

confirming that the three-dimensional contour does not intersect an edge of an edge of a field-of-view of the three-dimensional sensor except at the hand wrist; and

determining that the three-dimensional contour is mostly flat in the depth dimension.

9. The system of claim 5 wherein the unrolling one or more two-dimensional fingerprints includes:

re-sampling vertices from the triangulated, three-dimensional surface mesh;

mapping the re-sampled vertices to a uniform two-dimensional grid;

computing axes for a regional surface for each region of the two-dimensional grid;

rotating each region of the two-dimensional grid to the computed axis for the region;

determining a local height for each pixel of the two-dimensional grid;

setting a pixel intensity for each pixel of the two-dimensional grid based on the determined local height; and

outputting the two-dimensional grid as the unrolled two-dimensional fingerprint.

10. The system of claim 1 further comprising enhancing the two-dimensional fingerprint.

11. The system of claim 1 further comprising an ultrasound sensor that detects when a subject hand is above the three-dimensional sensor, thereby causing the three-dimensional sensor to generate the three-dimensional surface data of a hand and one or more fingers of a subject.

12. The system of claim 1 wherein the system is portable and further comprises a carrying case that encloses the three-dimensional sensor, the processor and the memory.

13. A method for extracting two-dimensional fingerprints from high resolution three-dimensional surface data obtained from contactless, stand-off sensors, comprising:

generating three-dimensional surface data of a hand and one or more fingers of a subject using a three-dimensional sensor;

collecting three-dimensional surface data of the subject hand and one or more subject fingers generated by the three-dimensional sensor;

estimating a hand pose of the subject based on the collected three-dimensional surface data;

based on the estimated hand pose, extracting fingerprint information from the collected three-dimensional surface data;

unrolling one or more two-dimensional fingerprints from the extracted fingerprint information;

determining a fingerprint quality score for each of the one or more two-dimensional fingerprints; and

for each of the one or more two-dimensional fingerprints that have a sufficiently high determined fingerprint quality score, storing the two-dimensional fingerprint.

14. The method of claim 13 wherein the generating three-dimensional surface data of the subject hand generates three-dimensional surface data that includes a dense set of surface points, wherein each point samples a three-dimensional position as well as other attributes of the one or more subject fingers including surface normal information and color.

15. The method of claim 14 wherein the collecting three-dimensional surface data includes generating a triangulated, three-dimensional surface mesh from the dense surface point set.

16. The method of claim 15 wherein the estimating a hand pose of the subject includes:

extracting a three-dimensional contour of the subject hand from the triangulated, three-dimensional surface mesh; and

performing a set of initial hand pose tests.

17. The method of claim 16 wherein the performing a set of initial hand pose tests includes:

locating the hand thumb in the three-dimensional contour;

verifying that the hand palm is facing towards the three-dimensional sensor;

confirming that the three-dimensional contour does not intersect an edge of an edge of a field-of-view of the three-dimensional sensor except at the hand wrist; and

determining that the three-dimensional contour is mostly flat in the depth dimension.

18. The method of claim 15 wherein the unrolling one or more two-dimensional fingerprints includes:

re-sampling vertices from the triangulated, three-dimensional surface mesh;

mapping the re-sampled vertices to a uniform two-dimensional grid;

computing axes for a regional surface for each region of the two-dimensional grid;

rotating each region of the two-dimensional grid to the computed axis for the region;

determining a local height for each pixel of the two-dimensional grid;

setting a pixel intensity for each pixel of the two-dimensional grid based on the determined local height; and

outputting the two-dimensional grid as the unrolled two-dimensional fingerprint.

19. The method of claim 13 further comprising enhancing the two-dimensional fingerprint.

20. The method of claim 13 further comprising detecting when a subject hand is above the three-dimensional sensor, thereby causing the generating of the three-dimensional surface data of a hand and one or more fingers of a subject.