Fingerprint matching using ridge feature maps

• US 20030169910A1
• Filed: 12/04/2002
• Published: 09/11/2003
• Est. Priority Date: 12/14/2001
• Status: Active Grant

• Current Assignee: Siemens Corp. (Siemens AG)
• Original Assignee: Siemens Corporate Research Incorporated (Siemens AG)
• Inventors: Reisman, James G., Ross, Arun
• Granted Patent: US 7,142,699 B2
• Time in Patent Office: Days
• US Class Current: 382/124
• CPC Class Codes: G06V 40/1365 Matching; Classification

Abstract

A method for matching fingerprint images is provided. The method includes the steps of acquiring a query image of a fingerprint; extracting a minutiae set from the query image; comparing the minutiae set of the query image with a minutiae set of at least one template image to determine transformation parameters to align the query image to the at least one template image and to determine a minutiae matching score; constructing a ridge feature map of the query image; comparing the ridge feature map of the query image to a ridge feature map of the at least one template image to determine a ridge feature matching score; and combining the minutiae matching score with the ridge feature matching score resulting in an overall score, the overall score being compared to a threshold to determine if the query image and the at least one template image match.

Claims

1. A method for matching fingerprint images, the method comprising the steps of:

acquiring a query image of a fingerprint;

extracting a minutiae set from the query image;

comparing the minutiae set of the query image with a minutiae set of at least one template image to determine transformation parameters to align the query image to the at least one template image and to determine a minutiae matching score;

constructing a ridge feature map of the query image;

comparing the ridge feature map of the query image to a ridge feature map of the at least one template image to determine a ridge feature matching score; and

combining the minutiae matching score with the ridge feature matching score resulting in an overall score, the overall score being compared to a threshold to determine if the query image and the at least one template image match.

2. The method as in claim 1, further comprising the step of enhancing the acquired query image.

3. The method as in claim 1, further comprising the step of segmenting foreground information from background information of the acquired query image.

4. The method as in claim 1, wherein the constructing a ridge feature map step comprises the steps of:

filtering the query image with a plurality of filters, a filtered query image resulting from each of the plurality of filters;

square tessellating each of the filtered query images into a plurality of cells;

measuring a variance of pixel intensities in each of the plurality of cells to determine a feature vector for each filtered query image;

combining the feature vectors of each of the filtered query images.

5. The method as in claim 4, wherein the plurality of filters are tuned to a frequency corresponding to an average inter-ridge spacing in the query image.

6. The method as in claim 4, wherein a size of each of the plurality of cells is determined to be about a width of two ridges of the fingerprint image.

7. The method as in claim 1, wherein the comparing the minutiae sets step comprises the step of generating a correspondence map pairing minutiae points from the query set and the at least one template set.

8. The method as in claim 4, wherein the ridge feature matching score is a sum of feature vector distances in corresponding tessellated cells.

9. The method as in claim 4, wherein the plurality of filters are rotated by the transformation parameters.

10. The method as in claim 1, wherein the at least one template image includes a plurality of template images and an overall matching score is determined for each of the plurality of template images.

11. The method as in claim 10, further comprising the step of determining a template image with the highest overall matching score, the highest matching score template image being a closest match to the query image.

12. A program storage device readable by machine, tangibly embodying a program of instructions executable by the machine to perform method steps for matching fingerprint images, the method comprising the steps of:

acquiring a query image of a fingerprint;

extracting a minutiae set from the query image;

comparing the minutiae set of the query image with a minutiae set of at least one template image to determine transformation parameters to align the query image to the at least one template image and to determine a minutiae matching score;

constructing a ridge feature map of the query image;

comparing the ridge feature map of the query image to a ridge feature map of the at least one template image to determine a ridge feature matching score; and

combining the minutiae matching score with the ridge feature matching score resulting in an overall score, the overall score being compared to a threshold to determine if the query image and the at least one template image match.

13. The program storage device as in claim 12, wherein the constructing a ridge feature map step comprises the steps of:

filtering the query image with a plurality of filters, a filtered query image resulting from each of the plurality of filters;

square tessellating each of the filtered query images into a plurality of cells;

measuring a variance of pixel intensities in each of the plurality of cells to determine a feature vector for each filtered query image;

combining the feature vectors of each of the filtered query images.

14. The program storage device as in claim 13, wherein the plurality of filters are tuned to a frequency corresponding to an average inter-ridge spacing in the query image.

15. The program storage device as in claim 13, wherein a size of each of the plurality of cells is determined to be about a width of two ridges of the fingerprint image.

16. The program storage device as in claim 12, wherein the comparing the minutiae sets step comprises the step of generating a correspondence map pairing minutiae points from the query set and the at least one template set.

17. The program storage device as in claim 13, wherein the ridge feature matching score is a sum of feature vector distances in corresponding tessellated cells.

18. The program storage device as in claim 13, wherein the plurality of filters are rotated by the transformation parameters.

19. A system for matching fingerprint images, the system comprising:

a fingerprint input device for acquiring a query image of a fingerprint; and

a processor for extracting a minutiae set from the query image, comparing the minutiae set of the query image with a minutiae set of at least one template image to determine transformation parameters to align the query image to the at least one template image and to determine a minutiae matching, score, constructing a ridge feature map of the query image, comparing the ridge feature map of the query image to a ridge feature map of the at least one template image to determine a ridge feature matching score, and combining the minutiae matching score with the ridge feature matching score resulting in an overall score, the overall score being compared to a threshold to determine if the query image and the at least one template image match.

20. The system as in claim 19, further comprising a storage device for storing the at least one template image.

21. The system as in claim 19, further comprising a display device for displaying a result of the match.

22. The system as in claim 19, wherein the fingerprint input device is a scanner type input device.

23. A method for matching fingerprint images, the method comprising the steps of:

acquiring a query image of a fingerprint;

constructing a ridge feature map of the query image;

aligning the ridge feature map of the query image to a ridge feature map of at least one template image;

comparing the ridge feature map of the query image to the ridge feature map of the at least one template image to determine a ridge feature matching score; and

comparing the ridge feature matching score to a threshold to determine if the query image and the at least one template image match.

24. The method as in claim 23, further comprising the step of enhancing the query image.

25. The method as in claim 23, wherein the constructing a ridge feature map step includes:

filtering the query image with a plurality of filters, a filtered query image resulting from each of the plurality of filters;

computing a standard deviation image for each of the plurality of filtered images;

sampling each standard deviation image in a horizontal and vertical direction to obtain a ridge feature image; and

compiling the ridge feature images to construct the ridge feature map.

26. The method as in claim 25, further comprising the step of expanding each ridge feature image to a size of each corresponding standard deviation image.

27. The method as in claim 26, wherein the aligning step comprises the steps of:

correlating the ridge feature map of the query image to the ridge feature map of the at least one template image by multiplying corresponding ridge feature images at all translation offsets; and

determining a sum of the correlations, wherein the maximum sum is chosen as the translation offset to align the maps.