Regional Fingerprint Liveness Detection Systems and Methods

• US 20080253626A1
• Filed: 10/10/2007
• Published: 10/16/2008
• Est. Priority Date: 10/10/2006
• Status: Active Grant

• Current Assignee: Precise Biometrics AB (Precise Biometrics Incorporated)
• Original Assignee: West Virginia University Research Corp., Wvu Office Of Technology Transfer & Wvu Business Incubator
• Inventors: Hornak, Lawrence, Shuckers, Stephanie, Tan, Bozhao
• Granted Patent: US 8,098,906 B2
• Time in Patent Office: Days
• US Class Current: 382/125
• CPC Class Codes: G06V 40/1376 Matching features related to ridge properties or fingerprint texture
• CPC Class Codes: G06V 40/1382 Detecting the live character of the finger, i.e. distinguishing from a fake or cadaver finger
• CPC Class Codes: G06V 40/1388 using image processing

Abstract

Various systems, methods, and programs embodied in computer-readable mediums are provided for fingerprint liveness detection. In one embodiment, a method for determining fingerprint liveness is provided that comprises receiving a fingerprint image; extracting a region of interest from the fingerprint image; generating a histogram of the region of interest; determining a statistical feature of the histogram; and determining liveness of the fingerprint image based upon the statistical feature.

Claims

1. A method for determining fingerprint liveness, comprising the steps of:

receiving a fingerprint image;

extracting a region of interest from the fingerprint image;

generating a histogram of the region of interest;

determining a statistical feature of the histogram; and

determining liveness of the fingerprint image based upon the statistical feature.

2. The method of claim 1, wherein the histogram is based upon grayscale variation of pixels within the region of interest.

3. The method of claim 1, wherein the step of determining a statistical feature of the histogram further comprises:

summing histogram distribution values over a predefined range of the histogram; and

normalizing the sum of histogram distribution values.

4. The method of claim 1, wherein the step of determining liveness of the fingerprint image further comprises performing a neural network analysis of the statistical feature.

5. The method of claim 1, wherein the step of determining liveness of the fingerprint image further comprises performing a classification tree analysis of the statistical feature.

6. The method of claim 5, wherein the classification tree analysis is based upon J48 classification.

7. The method of claim 1, wherein the step of extracting a region of interest further comprises the steps of:

dividing the fingerprint image into blocks;

determining a variance for each image block;

removing image blocks based upon the variance and a predetermined threshold;

determining a center point of the remaining image; and

extracting a region of interest about the center point.

8. The method of claim 7, wherein the variance is based upon intensity variation of pixels within each image block.

9. The method of claim 7, wherein the region of interest is a predefined area centered at the center point.

10. The method of claim 9, wherein the predefined area is square.

11. A system, comprising:

a processor circuit having a processor and a memory;

a detection system stored in the memory and executable by the processor, the detection system comprising;

logic that receives a fingerprint image;

logic that extracts a region of interest from the fingerprint image;

logic that generates a histogram of the region of interest;

logic that determines a statistical feature of the histogram; and

logic that determines liveness of the fingerprint image based upon the statistical feature.

12. The system of claim 11, wherein the logic that extracts a region of interest further comprises:

logic that divides the fingerprint image into blocks;

logic that determines a variance for each image block;

logic that removes image blocks based upon the variance and a predetermined threshold;

logic that determines a center point of the remaining image; and

logic that extracts a region of interest about the center point.

13. The system of claim 12, wherein the variance is based upon intensity variation of pixels within each image block.

14. The system of claim 11, wherein the logic that determines a statistical feature of the histogram further comprises:

logic that sums histogram distribution values over a predefined range of the histogram; and

logic that normalizes the sum of histogram distribution values.

15. The system of claim 11, wherein the logic that determines liveness of the fingerprint image further comprises logic to perform a classification tree analysis of the statistical feature.

16. A system, comprising:

means for receiving a fingerprint image;

means for extracting a region of interest from the fingerprint image;

means for generating a histogram of the region of interest;

means for determining a statistical feature of the histogram; and

means for determining liveness of the fingerprint image based upon the statistical feature.

17. The method of claim 16, wherein the means for extracting a region of interest further comprises:

means for dividing the fingerprint image into blocks;

means for determining a variance for each image block;

means for removing image blocks based upon the variance and a predetermined threshold;

means for determining a center point of the remaining image; and

means for extracting a region of interest about the center point.

18. The system of claim 16, wherein the means for determining a statistical feature of the histogram further comprises:

means for summing histogram distribution values over a predefined range of the histogram; and

means for normalizing the sum of histogram distribution values.

19. The system of claim 16, wherein the means for determining liveness of the fingerprint image further comprises means for performing a classification tree analysis of the statistical feature.