Systems and methods for performing fingerprint based user authentication using imagery captured using mobile devices

• US 10,521,643 B2
• Filed: 09/14/2017
• Issued: 12/31/2019
• Est. Priority Date: 02/06/2015
• Status: Active Grant

• Current Assignee: Veridium IP Limited (Harvard Investments LP)
• Original Assignee: Veridium IP Limited (Harvard Investments LP)
• Inventors: Mather, Jonathan Francis, Othman, Asem, Tyson, Richard, Simpson, Andrew
• Primary Examiner(s): Strege, John B
• Application Number:
  US15/704,561
• Publication Number:
  US 20180018501A1
• Time in Patent Office: 838 Days
• CPC Class Codes: G06T 7/11 Region-based segmentation
• CPC Class Codes: G06V 40/12 Fingerprints or palmprints
• CPC Class Codes: G06V 40/1341 Sensing with light passing through the finger
• CPC Class Codes: G06V 40/1347 Preprocessing; Feature extraction
• CPC Class Codes: G06V 40/1353 Extracting features related to minutiae or pores
• CPC Class Codes: G06V 40/1359 Extracting features related to ridge properties; Determining the fingerprint type, e.g. whorl or loop
• CPC Class Codes: G06V 40/1365 Matching; Classification
• CPC Class Codes: G06V 40/1371 Matching features related to minutiae or pores
• 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
• CPC Class Codes: G06V 40/1394 using acquisition arrangements

Abstract

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.

Claims

1. A method for performing fingerprint recognition, the method comprising:

capturing, by a mobile device having a camera, a storage medium, instructions stored on the storage medium, and a processor configured by executing the instructions, images depicting a plurality of fingers of a subject;

detecting, with the processor applying a plurality of finger detection algorithms, the plurality of fingers depicted in one or more of the images using a finger detection algorithm, wherein the plurality of finger detection algorithms include cascade classifiers;

based on the detecting, processing, with the processor, at least one image using a segmentation algorithm to identify a respective fingertip segment for one or more of the fingers detected as being depicted in the at least one image;

extracting, with the processor for each finger, discriminatory features from the respective fingertip segment;

generating a biometric identifier including the extracted discriminatory features; and

storing the generated biometric identifier in the memory with the processor.

2. The method of claim 1, wherein the plurality of finger detection algorithms are selected and applied by the processor based on one or more of:

measured environmental conditions, hardware capabilities of the mobile device, and one or more expected characteristics of the fingers to be detected.

3. The method of claim 1, further comprising:

determining, with the processor from one or more of the images, that the plurality of fingers within the one or more images are positionally stable.

4. The method of claim 1, further comprising:

computing an adaptive skin model based on one or more of the images; and

processing the one or more images based on the adaptive skin model.

5. The method of claim 4, wherein processing according to the adaptive skin model comprises:

enhancing the at least one image with the processor, wherein enhancing includes brightening regions of the at least one image having pixels determined to represent skin relative to regions having pixels determined to not represent skin.

6. The method of claim 1, wherein extracting discriminatory features from the respective fingertip segment comprises:

extracting from the respective fingertip segment, minutiae of a respective finger according to a minutiae extracting algorithm.

7. The method of claim 1, further comprising:

capturing, with the processor using the camera, the at least one image in response to detecting the plurality of fingers depicted in one or more of the images.

8. The method of claim 1, further comprising:

capturing, with the camera, the plurality of images as a feed of images;

displaying, with the processor on a display, the feed of images in near-real time and a finger placement guide overlaid over the feed;

detecting, with the processor using a finger finding algorithm, the plurality of fingers depicted in one or more images of the feed;

determining, with the processor, whether the detected plurality of fingers are aligned with the finger placement guide; and

capturing, with the processor using the camera, the at least one image in response to detecting an alignment of the plurality of fingers with the guide.

9. The method of claim 1, further comprising:

matching, with the processor, the generated biometric identifier to a previously stored biometric identifier associated with the user;

generating, based on the matching, a similarity score between the generated biometric identifier and the stored biometric identifier; and

verifying that the subject is the user based on the similarity score.

10. A method for performing fingerprint recognition, the method comprising:

capturing, by a mobile device having a camera, a storage medium, instructions stored on the storage medium, and a processer configured by extracting the instructions, images depicting a plurality of fingers of a subject;

detecting, with the processor using a finger detection algorithm, the plurality of fingers depicted in one or more of the images using a finger detection algorithm, wherein the step of detecting the one or more fingers comprises;

selecting at least a first finger detection algorithm and a second finger detection algorithm,

detecting, by the processor using the first and second finger detection algorithms, at least one candidate set of fingers depicted in the one or more images, wherein the first and second finger detection algorithms are classifiers, and wherein the second finger detection algorithm is a classifier that is trained differently from the first finger detection algorithm,

computing a quality metric representing a likelihood that the at least one candidate set of fingers represents the plurality of fingers, and

based on the quality not meeting a prescribed threshold, repeating the preceding detecting and computing steps to detect one or more other candidate sets of fingers and compute a respective quality metric;

based on the detecting, processing, with the processor, at least one image using a segmentation algorithm to identify a respective fingerprint segment for one or more of the fingers detected as being depicted in the at least one image;

extracting, with the processor for each finger, discriminatory features from the respective fingertip segment;

generating a biometric identifier including the extracted discriminatory features; and

storing the generated biometric identifier in the memory with the processor.

11. A method for performing fingerprint recognition, the method comprising:

capturing, by a mobile device having a camera, a storage medium, instructions stored on the storage medium, and a processor configured by executing the instructions, images depicting a plurality of fingers of a subject;

detecting, with the processor using a finger detection algorithm, the plurality of fingers depicted in one or more of the images using a finder detection algorithm;

based on the detecting, processing, with the processor, at least one image using a segmentation algorithm to identify a respective fingertip segment for one or more of the fingers detected as being depicted in the at least one image, wherein the step of processing at least one image using a segmentation algorithm to identify a respective fingertip segment for one or more fingers comprises;

analyzing, with the processor using one or more classifiers, at least a portion of the at least one image that depicts the plurality of fingers,

identifying candidate fingertip segments and assigning a respective score using the one or more classifiers, and

selecting the respective fingertip segment for the one or more fingers from among the set of candidate fingertip segments based on the respective scores;

extracting, with the processor for each finger, discriminatory features from the respective fingertip segment;

generating a biometric identifier including the extracted discriminatory features; and

storing the generated biometric identifier in the memory with the processor.

12. A method for performing fingerprint recognition, the method comprising:

capturing, by a mobile device having a camera, a storage medium, instructions stored on the storage medium, and a processor configured by executing the instructions, images depicting a plurality of fingers of a subject;

detecting, with the processor using a finger detection algorithm, the plurality of fingers depicted in one or more of the images;

processing, with the processor from at least one image using a segmentation algorithm, to identify a respective fingertip segment for one or more fingers depicted in the at least one image;

extracting, with the processor for each finger, discriminatory features from the respective fingertip segment;

generating a biometric identifier including the extracted discriminatory features, wherein generating the biometric identifier includes;

determining, for the respective fingertip segment depicted in the at least one of the images, a frequency of fingerprint ridges, and

scaling the biometric identifier based on the frequency of fingerprint ridges and a prescribed reference frequency; and

storing the generated biometric identifier in the memory with the processor.

13. A method for performing fingerprint recognition, the method comprising:

capturing, by a mobile device having a camera, a storage medium, instructions stored on the storage medium, and a processor configured by executing the instructions, images depicting a plurality of fingers of a subject, and wherein capturing includes capturing a first image depicting the plurality of fingers at a first position relative to the camera and a second image depicting the plurality of fingers at a second position relative to the camera, wherein the first and second positions are different;

detecting, with the processor using a finger detection algorithm, the plurality of fingers depicted in one or more of the images;

processing, with the processor from at least one image using a segmentation algorithm, to identify a respective fingertip segment for one or more fingers depicted in the at least one image;

extracting, with the processor for each finger, discriminatory features from the respective fingertip segment;

generating a biometric identifier including the extracted discriminatory features;

storing the generated biometric identifier in the memory with the processor;

determining, from at least the first and second images depicting the plurality of fingers from different respective positions relative to the camera, that the plurality of fingers are three-dimensional objects; and

verifying the subject is a live subject based on the determination that the plurality of fingers are three-dimensional objects.

14. A system for performing fingerprint recognition comprising:

a mobile device having a camera, a storage medium, a display, and a processor in operative communication with the camera, the display and the storage medium;

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;

capture images depicting a plurality of fingers of a subject using the camera,

detect, by applying a plurality of finger detection algorithms, the plurality of fingers depicted in one or more of the images, wherein the plurality of finger detection algorithms include cascade classifiers,

based on the detection of the plurality of fingers, process at least one image using a segmentation algorithm, to identify a respective fingertip segment for one or more fingers detected as being depicted in the at least one image,

extract, for each finger, discriminatory features from the respective fingertip segment,

generate a biometric identifier including the extracted discriminatory features, and

store the generated biometric identifier in the memory.

15. The system of claim 14, wherein the software application configures the processor to select and apply the plurality of finger detection algorithms based on one or more expected characteristics of the fingers to be detected.

16. The system of claim 14, wherein the software application further configures the processor to:

compute an adaptive skin model based on one or more of the images; and

process the one or more images based on the adaptive skin model.

17. The system of claim 16, wherein the processor is configured to process the one or more images according to the adaptive skin model by:

enhancing the at least one image, wherein enhancing includes brightening regions of the at least one image having pixels determined to represent skin relative to regions having pixels determined to not represent skin.

18. The system of claim 14, wherein the processor is configured to extract discriminatory features from the respective fingertip segment by:

extracting from the respective fingertip segment, minutiae of a respective finger according to a minutiae extracting algorithm.

19. The system of claim 14, wherein the software application further configures the processor to:

capture, with the processor using the camera, the at least one image in response to detecting the plurality of fingers depicted in one or more of the images.

20. The system of claim 14, wherein the software application further configures the processor to:

capture, with the camera, the plurality of images as a feed of images;

display, with the display, the feed of images in near-real time and a finger placement guide overlaid over the feed;

detect, using a finger finding algorithm, the plurality of fingers depicted in one or more images of the feed;

determine whether the detected plurality of fingers are aligned with the finger placement guide; and

capture, using the camera, the at least one image in response to detecting an alignment of the plurality of fingers with the guide.

21. A system for performing fingerprint recognition comprising:

a mobile device having a camera, a storage medium, a display, and a processor in operative communication with the camera, the display and the storage medium;

a software application comprising instruction in the form of code stored on the storage medium, wherein the instructions are executable in the processor and configure the processor to;

capture images depicting a plurality of fingers of a subject using the camera,

detect, using a finger detection algorithm, the plurality of fingers depicted in one or more of the images, wherein the software application configures the processor to detect the one or more fingers by;

selecting at least a first finger detection algorithm and a second finger detection algorithm, wherein the first and second finger detection algorithms are classifiers, and wherein the second finger detection algorithm is a classifier that is trained differently from the first finger detection algorithm;

detecting, by the processor using the first and second finger detection algorithms, at least one candidate set of fingers depicted in the one or more images;

computing a quality metric representing a likelihood that the at least one candidate set of fingers represents the plurality of fingers; and

based on the quality not meeting a prescribed threshold, repeating the preceding detecting and computing steps to detect one or more other candidate sets of fingers and compute a respective quality metric;

based on the detection of the plurality of fingers, process at least on image using a segmentation algorithm, to identify a respective fingertip segment for one or more fingers detected as being depicted in the at least one image,

extract, for each finger, discriminatory features from the respective fingertip segment,

generate a biometric identifier including the extracted discriminatory features, and

store the generated biometric identifier in the memory.

22. A system for performing fingerprint recognition comprising:

a mobile device having a camera, a storage medium, a display, and a processor in operative communication with the camera, the display and the storage medium;

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;

capture images depicting a plurality of fingers of a subject using the camera,

detect, using a finger detection algorithm, the plurality of fingers depicted in one or more of the images,

based on the detection of the plurality of fingers, process at least one image using a segmentation algorithm, to identify a respective fingertip segment for one or more fingers detected as being depicted in the at least one image, wherein the processor is configured to process the at least one image by;

analyzing, using one or more classifiers, at least a portion of the at least one image that depicts the plurality of fingers,

identifying candidate fingertip segments and assign a respective score using the one or more classifiers, and

selecting the respective fingertip segment for the one or more fingers from among the set of candidate fingertip segments based on the respective scores;

extract, for each finger, discriminatory features from the respective fingertip segment,

generate a biometric identifier including the extracted discriminatory features, and

store the generated biometric identifier in the memory.

23. A system for performing fingerprint recognition comprising:

a mobile device having a camera, a storage medium, a display, and a processor in operative communication with the camera, the display and the storage medium; and

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;

capture images depicting a plurality of fingers of a subject using the camera,

detect, using a finger detection algorithm, the plurality of fingers depicted in one or more of the images,

process at least one image using a segmentation algorithm, to identify a respective fingertip segment for one or more fingers depicted in the at least one image,

extract, for each finger, discriminatory features from the respective fingertip segment,

generate a biometric identifier including the extracted discriminatory features,

determine a frequency of fingerprint ridges for the respective fingertip segment depicted in the at least one of the images,

scale the biometric identifier based on the frequency of fingerprint ridges and a prescribed reference frequency, and

store the generated biometric identifier in the memory.

24. A system for performing fingerprint recognition comprising:

a mobile device having a camera, a storage medium, a display, and a processor in operative communication with the camera, the display and the storage medium; and

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;

capture, using the camera, images depicting a plurality of fingers of a subject including a first image depicting the plurality of fingers at a first position relative to the camera and a second image depicting the plurality of fingers at a second position relative to the camera, wherein the first and second positions are different,

detect, using a finger detection algorithm, the plurality of fingers depicted in one or more of the images,

process at least one image using a segmentation algorithm, to identify a respective fingertip segment for one or more fingers depicted in the at least one image,

extract, for each finger, discriminatory features from the respective fingertip segment,

generate a biometric identifier including the extracted discriminatory features,

store the generated biometric identifier in the memory,

determine, from at least the first and second images depicting the plurality of fingers from different respective positions relative to the camera, that the plurality of fingers are three-dimensional objects, and

verify the subject is a live subject based on the determination that the plurality of fingers are three-dimensional objects.