Systems and methods for performing fingerprint based user authentication using imagery captured using mobile devices
Technologies are presented herein in support of a system and method for performing fingerprint recognition. Embodiments of the present invention concern a system and method for capturing a user's biometric features and generating an identifier characterizing the user's biometric features using a mobile device such as a smartphone. The biometric identifier is generated using imagery captured of a plurality of fingers of a user for the purposes of authenticating/identifying the user according to the captured biometrics and determining the user's liveness. The present disclosure also describes additional techniques for preventing erroneous authentication caused by spoofing. In some examples, the anti-spoofing techniques may include capturing one or more images of a user's fingers and analyzing the captured images for indications of liveness.
1. A method of enhancing a fingerprint image for performing fingerprint recognition of a user via a mobile device having a camera, a storage medium, instructions stored on the storage medium, and a processor configured by executing the instructions, the method comprising:
receiving, at the processor, a fingerprint image depicting a fingerprint of the user and captured using the camera of the mobile device;
identifying, with the processor using a finger detection algorithm, a fingertip segment in the fingerprint image;
enhancing, with the processor, the fingerprint image, wherein the enhancing of the fingerprint image comprises:
processing, with the processor using an analysis module, the fingertip segment to enhance detail of the image captured by the camera of the mobile device to mimic a quality and attributes of fingerprint impression images captured from live scan sensors,
generating an enhanced fingerprint image that mimics attributes of fingerprint impression images captured from live scan sensors and is suitable for matching with fingerprint impression images captured from live scan sensors, wherein one of the attributes is a frequency of fingerprint ridges, wherein the generating step includes scaling the enhanced fingerprint image according to a prescribed reference frequency of fingerprint ridges, wherein the prescribed reference frequency is an attribute of images stored in the storage medium that were captured from live scan sensors, and
identifying, with the processor, discriminatory fingerprint features from the fingertip segment of the enhanced fingerprint image; and
storing the enhanced fingerprint image in the storage medium as a representation of the discriminatory features.
2. The method of claim 1 , wherein the enhancing of the fingerprint image comprises:
brightening regions of the fingerprint image that have pixels determined to represent skin relative to regions having pixels determined to not represent skin based on p-values for the pixels in an adaptive color model.
3. The method of claim 1 , wherein the enhancing of the fingerprint image comprises:
implementing an enhancement filter on the fingertip segment to boost a contrast between ridges and furrows of the fingerprint in the fingertip segment, the enhancement filter including a histogram equalization.
4. The method of claim 1 , wherein the processing includes applying a set of Gabor filters tuned to a smoothed ridge orientation map.
5. The method of claim 1 , further comprising the steps of:
comparing the representation of the discriminatory features to a stored biometric identifier corresponding to the user, wherein the stored biometric identifier is a fingerprint impression image captured from a live scan sensor; and
authenticating the identity of the user if the representation of the discriminatory features match the corresponding features of the stored biometric identifier corresponding to the user.
6. The method of claim 1 , further comprising: transmitting the enhanced fingerprint image to a remote computing system for matching the enhanced fingerprint image to an Integrated Automated Fingerprint Identification Systems (IAFIS) database of fingerprint impression images.
7. The method of claim 1 , further comprising:
determining, with the processor from the fingerprint image, a liveness of the user.
8. The method of claim 1 , wherein the step of enhancing the image comprises enhancing discriminatory features depicted in the image of the fingertip segment, and excluding non-discriminatory features from the image of the fingertip segment.
9. The method of claim 1 , further comprising:
scaling the enhanced fingerprint image; and
storing the enhanced fingerprint image in the storage medium as the representation of the discriminatory features.
10. The method of claim 1 , further comprising:
normalizing the frequency of the fingerprint ridges of the enhanced fingerprint image to a reference frequency.
11. The method of claim 1 , wherein the step of generating the enhanced fingerprint image further comprises:
applying a filter to the enhanced fingerprint image to remove frequencies that do not correspond to the frequency of the fingerprint ridges.
12. A system for enhancing a fingerprint image for performing fingerprint recognition of a user via a mobile device having a camera, a storage medium, and a processor in operative communication with the camera and the storage medium, the system comprising:
a software application comprising instructions in the form of code stored on the storage medium, wherein the instructions are executable in the processor and configure the processor to:
receive a fingerprint image depicting a fingerprint of the user captured using the camera of the mobile device;
identify, using a finger detection algorithm, a fingertip segment in the fingerprint image;
enhance the fingerprint image, wherein to enhance the fingerprint image, the processor is configured to:
process, using an analysis module, the fingertip segment to enhance the detail of the image captured by the camera of the mobile device to mimic a quality and attributes of fingerprint impression images captured from live scan sensors, and
wherein the processor is further configured to generate an enhanced fingerprint image that mimics attributes of fingerprint impression images captured from live scan sensors and wherein the enhanced fingerprint image is suitable for matching with fingerprint impression images captured from live scan sensors, wherein one of the attributes is a frequency of fingerprint ridges,
scale the enhanced fingerprint image according to a prescribed reference frequency of fingerprint ridges, the prescribed reference frequency being an attribute of images stored in the storage medium that were captured from live scan sensors, and
identify discriminatory fingerprint features from the fingertip segment of the enhanced fingerprint image; and
store the enhanced fingerprint image in the storage medium as a representation of the discriminatory features.
13. The system of claim 12 , wherein to enhance the fingerprint image, the processor is configured to:
brighten regions of the fingerprint image that have pixels determined to represent skin relative to regions having pixels determined to not represent skin based on p-values for the pixels in an adaptive color model.
14. The system of claim 12 , wherein to enhance the fingerprint image, the processor is configured to:
implement an enhancement filter on the fingertip segment to boost a contrast between ridges and furrows of the fingerprint in the fingertip segment, the enhancement filter including a histogram equalization.
15. The system of claim 12 , wherein to process the fingertip segment, the processor is configured to apply a set of Gabor filters tuned to a smoothed ridge orientation map.
16. The system of claim 12 , wherein the processor is further configured to:
scale the enhanced fingerprint image according to a frequency of fingerprint ridges; and
store the enhanced fingerprint image in the storage medium as the representation of the discriminatory features.
17. The system of claim 16 , wherein the processor is further configured to:
normalize the frequency of the fingerprint ridges of the enhanced fingerprint image to a reference frequency.
18. The system of claim 12 , wherein the processor is further configured to:
compare the representation of the discriminatory features to a stored biometric identifier corresponding to the user, wherein the stored biometric identifier is a fingerprint impression image captured from a live scan sensor; and
authenticate the identity of the user if the representation of the discriminatory features match the corresponding features of the stored biometric identifier corresponding to the user.
19. The system of claim 12 , wherein the processor is further configured to:
transmit the enhanced fingerprint image to a remote computing system for matching the enhanced fingerprint image to an Integrated Automated Fingerprint Identification Systems (IAFIS) database of fingerprint impression images.
20. The system of claim 12 , wherein the processor is further configured to:
determine, from the fingerprint image, a liveness of the user.
21. The system of claim 12 , wherein to enhance the fingerprint image, the processor is configured to:
enhance discriminatory features depicted in the image of the fingertip segment; and
exclude non-discriminatory features from the image of the fingertip segment.
22. The system of claim 12 , wherein to generate the enhanced fingerprint image, the processor is further configured to:
apply a filter to the enhanced fingerprint image to remove frequencies that do not correspond to the frequency of the fingerprint ridges.