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

• US 9,785,823 B2
• Filed: 07/18/2016
• Issued: 10/10/2017
• 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:
  US15/212,335
• Publication Number:
  US 20160321496A1
• Time in Patent Office: 449 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 one or more fingers of a subject;

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

determining, with the processor from one or more of the images, that the one or more fingers within the one or more images are positionally stable, wherein determining that the one or more fingers are positionally stable comprises;

determining, with the processor according to an object tracking algorithm, a respective position of the one or more fingers in a first image and a respective change in position of the one or more fingers throughout a sequence of subsequent images among the images,

calculating a speed of movement of the one or more fingers based on the respective change in position, and

verifying that the one or more fingers are positionally stable based on the speed falling below a threshold velocity;

identifying, based on determining that the one or more fingers within the one or more images are positionally stable, with the processor from at least one of the images according to a segmentation algorithm, a respective fingertip segment for each finger among the one or more fingers;

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

generating a biometric identifier including the extracted discriminatory features;

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

2. The method of claim 1, wherein the step of determining according to the object tracking algorithm comprises:

dynamically switching between a first object tracking algorithm and a second object tracking algorithm based on the determined position and change in position.

3. The method of claim 2, further comprising:

applying a first object tracking algorithm to determine the position of the one or more fingers in the first image;

applying, based on the identified first position, a second object tracking algorithm to determine a respective position of the one or more fingers in a subsequent image in the sequence.

4. The method of claim 3, further comprising:

re-applying the first object tracking algorithm to determine the respective position of the one or more fingers in the subsequent image upon detecting a failure of the second object tracking algorithm, wherein the failure is detected as a function of the change in position of the one or more fingers between images in the sequence exceeding a threshold.

5. The method of claim 3, wherein the first object tracking algorithm is a classifier, and wherein the second object tracking algorithm is one or more of a template matching algorithm and an optical flow tracking algorithm.

6. The method of claim 1, wherein extracting discriminatory features for each of the respective fingertip segments comprises:

extracting from each of the respective fingertip segments, minutiae of a respective finger according to a minutiae extracting algorithm; and

for each of the one or more fingers, encoding respective feature vectors representing the extracted minutia in the biometric identifier.

7. The method of claim 6, further comprising:

comparing, with the processor, each of the encoded feature vectors to a previously stored feature vector associated with the user;

computing similarity scores based on the comparison;

verifying that similarity scores individually computed for a prescribed number of fingers among the one or more fingers exceed a secondary matching threshold, and that a combination of the computed similarity scores exceeds a primary matching threshold; and

determining that the subject is the user based on the verification.

8. The method of claim 6, further comprising:

identifying, with the processor from at least one of the images according to a segmentation algorithm, a respective intermediate phalange segment for each finger among the one or more fingers;

extracting, with the processor for each finger, discriminatory features from the respective intermediate phalange segment; and

generating a biometric identifier including the discriminatory features extracted from the intermediate phalange segments.

9. The method of claim 1, further comprising:

detecting, by the processor in a first image using a first object tracking algorithm, one or more fingers;

calculating a first position of the detected one or more fingers in the first image;

determining, with the processor applying a second object tracking algorithm to a sequence of subsequent images among the images, respective positions of the one or more fingers throughout the sequence of subsequent images,

performing the step of determining that the one or more fingers are positionally stable based on the respective positions.

10. The method of claim 9, wherein the first object tracking algorithm is a classifier, and wherein the second object tracking algorithm is one or more of a template matching algorithm and an optical flow tracking algorithm and wherein the step of determining the respective positions of the one or more fingers throughout the sequence of subsequent images comprises:

analyzing, a search region within a respective image in the sequence of images using the second object tracking algorithm, wherein analyzing includes;

detecting the one or more fingers in the search region, and

calculating a respective position of the one or more fingers, wherein the search region for the respective image is defined according to one or more of the first position and a calculated position of the one or more fingers as determined from a preceding image in the sequence of images.

11. The method of claim 10, wherein the first position and the respective positions calculated by the processor include an absolute position of the one or more fingers and a relative position of distinct features of one or more fingers.

12. The method of claim 11, wherein the second object tracking algorithm performs the steps of:

detecting pixels within the search region of the respective image that represent distinct finger features; and

comparing the detected pixels to expected physical characteristics of the one or more fingers, wherein the expected physical characteristics include one or more of;

a relative width of one or more fingers,

a relative length of one or more finger,

a relative position in a horizontal direction of one or more finger features, and

a relative position in a vertical direction of one or more finger features.

13. The method of claim 1, further comprising:

determining, with the processor, that one or more images among the images are in focus prior to prior to performing the detecting step.

14. The method of claim 1, further comprising:

comparing, with the processor, the biometric identifier to each of a plurality of previously stored biometric identifiers associated with the user;

computing respective similarity scores based on the comparison of the biometric identifier to each of a plurality of previously stored biometric identifiers;

computing a combined match score based on the respective similarity scores; and

determining that the subject is the user based on the combined match score exceeding a threshold match score.

15. The method of claim 1, wherein the step of generating the biometric identifier further comprises:

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.

16. 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 one or more fingers of a subject;

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

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

computing an adaptive skin model based on one or more of the images, wherein computing an adaptive skin model, comprises;

detecting a region within the one or more images including pixels having color values that correspond to an expected skin tone;

computing a color model for the region based on the pixels;

fitting, with the processor, a probability density function (PDF) to distributions of hue and saturation for the pixels within the detected region;

locating, with the processor applying the PDF to the one or more images, additional pixels in the image meeting the PDF;

computing, for each located pixel, a p-value representing a likelihood that the pixel represents skin;

refine the computed color model based on the identified pixels having a p-value that exceeds a threshold p-value;

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

identifying, based on determining that the one or more fingers within the one or more images are positionally stable, with the processor from at least one of the images according to a segmentation algorithm, a respective fingertip segment for each finger among the one or more fingers;

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

generating a biometric identifier including the extracted discriminatory features;

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

17. The method of claim 16, the step of computing an adaptive skin model further comprising:

iteratively repeated the locating, computing and refining step until the number of pixels that define the refined model reaches convergence.

18. The method of claim 16, wherein processing according to the adaptive skim model comprises one or more of the following steps:

identifying the respective fingertip segment for each finger among the one or more fingers by applying a classifier to the adaptive skin model; and

enhancing the one or more images, with the processor, prior to identifying the respective fingertip segment, wherein enhancing includes brightening regions of the one or more images having pixels determined to represent skin relative to regions having pixels determined to not represent skin based on the p-values for the pixels in the adaptive color model.

19. A method for performing biometric 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 one or more biometric features of a subject;

detecting, with the processor using a feature detection algorithm, the one or more biometric features depicted in one or more of the images;

calculating, with the processor, a first position of the one or more biometric features in a first image among the images;

determining, with the processor applying an object tracking algorithm to a sequence of subsequent images among the images, respective positions of the one or more biometric features throughout the sequence of subsequent images;

calculating a speed of movement of the one or more biometric features based on the first position of the one or more biometric features and the respective positions of the one or more biometric features throughout the sequence of subsequent images;

determining, with the processor, that the one or more biometric features are positionally stable within the one or more images based on the calculated speed of movement of the one or more biometric features falling below a threshold;

based on determining that the one or more biometric features are positionally stable, identifying, with the processor from at least one of the images according to a segmentation algorithm, a respective segment within the at least one image, wherein the segmentation algorithm distinguishes the one or more biometric features from surrounding portions of the at least one image;

extracting, with the processor for each of the one or more biometric features, discriminatory features from the respective segment;

generating a biometric identifier including the extracted discriminatory features; and

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

20. The method of claim 19, wherein the feature detection algorithm is a classifier, and wherein the object tracking algorithm is one or more of a template matching algorithm and an optical flow tracking algorithm and wherein the step of determining the respective positions of the one or more biometric features throughout the sequence of subsequent images comprises:

detecting the one or more features within a search region within a respective image in the sequence of images using the object tracking algorithm;

calculating a respective position of the detected one or more biometric features, wherein the search region for the respective image is defined according to one or more of the first position and a calculated position of the one or more fingers as determined from a preceding image in the sequence of images.