Derived virtual quality parameters for fingerprint matching

1. A method comprising:

obtaining data indicating (i) a list of minutiae extracted from a fingerprint image, and (ii) for each minutia included in the list of minutiae, an octant feature vector that identifies one or more neighboring minutiae within the fingerprint image;

for each minutia included in the list of minutiae:

computing one or more parameters based on comparing features of a minutia and respective features of one or more neighboring minutiae for the minutia, and

computing an aggregate minutia quality confidence score based on combining the one or more computed parameters;

computing a fingerprint quality confidence score for the fingerprint image based at least on combining the aggregate minutia quality confidence scores; and

providing the fingerprint quality confidence score for output.

2. The method of claim 1 , wherein:

combining the aggregate minutia quality confidence scores comprises determining a number of minutiae within the list of minutiae having a number of neighboring minutiae that satisfies a threshold; and

the fingerprint quality confidence score is computed based at least on the determined number of minutiae within the list of minutiae having a number of neighboring minutiae that satisfies a threshold.

3. The method of claim 1 , wherein the one or more parameters comprise at least one of:

a calculated distance difference between each minutia included in the list of minutiae and one or more neighboring minutiae for each minutia;

a number of neighbor minutiae for each minutia included in the list of minutiae;

a number of minutiae included in the list of minutiae that are located inside a close radius threshold; or

a number of minutiae included in the list of minutiae that are located outside a far radius threshold.

4. The method of claim 1 , further comprising:

computing a fingerprint similarity score between the fingerprint image and a reference fingerprint image based at least on a value of the fingerprint quality confidence score.

5. The method of claim 4 , wherein the fingerprint similarity score between the fingerprint image and the reference fingerprint image is computed additionally based on (i) a number of minutiae within the list of minutiae that are identified as mated minutiae, and (ii) a number of minutiae within the list of minutiae that are identified as non-mated minutiae.

6. The method of claim 5 , further comprising:

computing a match quality confidence score based on the number of minutiae within the list of minutiae that are identified as mated minutiae;

computing a non-match minutiae quality confidence score based on the number of minutiae within the list of minutiae that are identified as non-mated minutiae; and

wherein the fingerprint similarity score is adjusted based at least on (i) a value of the match quality confidence score, and (ii) a value of the non-match minutia quality confidence score.

7. The method of claim 6 , wherein adjusting the value of the fingerprint similarity score comprises:

computing at least an area within the fingerprint image that corresponds to an overlapping region between the fingerprint image and the reference fingerprint image;

classifying, based at least on the computed area within the fingerprint image, each of the minutiae included in the list of minutiae to one or more quality indicative groups; and

adjusting a value of the fingerprint similarity score based at least on a number of minutiae classified as each of the one or more quality indicative groups.

8. The method of claim 7 , wherein the one or more quality indicative groups comprises a mated minutiae quality group and a non-mated minutiae quality group.

9. A system comprising:

one or more computers; and

one or more storage devices storing instructions that, when executed by the one or more computers, cause the one or more computers to perform operations comprising:

obtaining data indicating (i) a list of minutiae extracted from a fingerprint image, and (ii) for each minutia included in the list of minutiae, an octant feature vector that identifies one or more neighboring minutiae within the fingerprint image;

for each minutia included in the list of minutiae:

computing one or more parameters based on comparing features of a minutia and respective features of one or more neighboring minutiae for the minutia, and

computing an aggregate minutia quality confidence score based on combining the one or more computed parameters;

computing a fingerprint quality confidence score for the fingerprint image based at least on combining the aggregate minutia quality confidence scores; and

providing the fingerprint quality confidence score for output.

10. The system of claim 9 , wherein:

combining the aggregate minutia quality confidence scores comprises determining a number of minutiae within the list of minutiae having a number of neighboring minutiae that satisfies a threshold; and

the fingerprint quality confidence score is computed based at least on the determined number of minutiae within the list of minutiae having a number of neighboring minutiae that satisfies a threshold.

11. The system of claim 9 , wherein the one or more parameters comprise at least one of:

a calculated distance difference between each minutia included in the list of minutiae and one or more neighboring minutiae for each minutia;

a number of neighbor minutiae for each minutia included in the list of minutiae;

a number of minutiae included in the list of minutiae that are located inside a close radius threshold; or

a number of minutiae included in the list of minutiae that are located outside a far radius threshold.

12. The system of claim 9 , further comprising:

computing a fingerprint similarity score between the fingerprint image and a reference fingerprint image based at least on a value of the fingerprint quality confidence score.

13. The system of claim 12 , wherein the fingerprint similarity score between the fingerprint image and the reference fingerprint image is computed additionally based on (i) a number of minutiae within the list of minutiae that are identified as mated minutiae, and (ii) a number of minutiae within the list of minutiae that are identified as non-mated minutiae.

14. The system of claim 13 , wherein the operations further comprise:

computing a match quality confidence score based on the number of minutiae within the list of minutiae that are identified as mated minutiae;

computing a non-match minutiae quality confidence score based on the number of minutiae within the list of minutiae that are identified as non-mated minutiae; and

wherein the fingerprint similarity score is adjusted based at least on (i) a value of the match quality confidence score, and (ii) a value of the non-match minutia quality confidence score.

15. The system of claim 14 , wherein adjusting the value of the fingerprint similarity score comprises:

computing at least an area within the fingerprint image that corresponds to an overlapping region between the fingerprint image and the reference fingerprint image;

classifying, based at least on the computed area within the fingerprint image, each of the minutiae included in the list of minutiae to one or more quality indicative groups; and

adjusting a value of the fingerprint similarity score based at least on a number of minutiae classified as each of the one or more quality indicative groups.

16. One or more non-transitory computer-readable media storing instructions that, when executed by one or more computers of a server system, cause the server system to perform operations comprising:

obtaining data indicating (i) a list of minutiae extracted from a fingerprint image, and (ii) for each minutia included in the list of minutiae, an octant feature vector that identifies one or more neighboring minutiae within the fingerprint image;

for each minutia included in the list of minutiae:

computing one or more parameters based on comparing features of a minutia and respective features of one or more neighboring minutiae for the minutia, and

computing an aggregate minutia quality confidence score based on combining the one or more computed parameters;

computing a fingerprint quality confidence score for the fingerprint image based at least on combining the aggregate minutia quality confidence scores; and

providing the fingerprint quality confidence score for output.

17. The one or more non-transitory computer-readable media of claim 16 , wherein:

combining the aggregate minutia quality confidence scores comprises determining a number of minutiae within the list of minutiae having a number of neighboring minutiae that satisfies a threshold; and

the fingerprint quality confidence score is computed based at least on the determined number of minutiae within the list of minutiae having a number of neighboring minutiae that satisfies a threshold.

18. The one or more non-transitory computer-readable media of claim 16 , wherein the one or more parameters comprise at least one of:

a calculated distance difference between each minutia included in the list of minutiae and one or more neighboring minutiae for each minutia;

a number of neighbor minutiae for each minutia included in the list of minutiae;

a number of minutiae included in the list of minutiae that are located inside a close radius threshold; or

a number of minutiae included in the list of minutiae that are located outside a far radius threshold.

19. The one or more non-transitory computer-readable media of claim 16 , further comprising:

computing a fingerprint similarity score between the fingerprint image and a reference fingerprint image based at least on a value of the fingerprint quality confidence score.

20. The one or more non-transitory computer-readable media of claim 19 , wherein the fingerprint similarity score between the fingerprint image and the reference fingerprint image is computed additionally based on (i) a number of minutiae within the list of minutiae that are identified as mated minutiae, and (ii) a number of minutiae within the list of minutiae that are identified as non-mated minutiae.