Systems and methods for performing iris identification and verification using mobile devices
Technologies are presented herein in support of a system and method for performing iris identification and verification using mobile devices. Embodiments of the present invention concern a method for authenticating a user with a mobile device that includes steps for capturing imagery of a user's face, analyzing the imagery to identify the portion of the image depicting the user's eyes and segmenting the eye image to isolate the iris image data and encoding the iris image data in iris template. The present disclosure further describes authenticating the user based on the encoded iris template and 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 eyes and analyzing the captured images for indications of liveness based on reflection characteristics depicted in the imagery.
1. A computer implemented method for authenticating a user using a mobile device based on imagery of one or more portions of facial region of the user, wherein the imagery is captured using a camera of the mobile device, the method comprising:
capturing, by a mobile device having a camera, a light emitter, a storage medium, instructions stored on the storage medium, and a processor configured by executing the instructions, a plurality of visible light images depicting at least one facial region of the user, wherein at least a first image is captured by the camera while the light emitter is activated and illuminating the user, and wherein at least a second image is captured while the light emitter is deactivated and is not illuminating the user, wherein the camera is configured to sense visible light, and wherein the light emitter is configured to emit visible light;
detecting, by the processor in at least the first and the second images from among the plurality of images, an eye of the user depicted in the respective images;
aligning, by the processor, at least the first image and the second image;
subtracting, by the processor, at least a portion of the first image from a corresponding portion of the second image;
detecting, by the processor based on a result of the image subtraction, a reflection characteristic of a cornea of the eye by analyzing the result to identify a specular reflection by the cornea and determine the reflection characteristic;
determining, by the processor, that the imagery depicts a live user by comparing the detected reflection characteristic to one or more prescribed reflection characteristics.
2. The method of claim 1 , wherein the step of aligning is performed using an algorithm that matches the second image to a template.
3. The method of claim 1 , wherein the step of aligning at least the first image and the second image is performed using an algorithm that matches an image pyramid of the second image to a template of the user's eye that was previously recorded on the storage medium.
4. The method of claim 1 , wherein the portion of the first image and corresponding portion of the second image each depict at least an iris of the user, and further comprising:
cropping, by the processor, at least the first and second images to isolate the portions of the respective images that depict the iris of the user.
5. The method of claim 1 , wherein the step of detecting a reflection characteristic further comprises:
analyzing, by the processor, the result to identify a reflection peak;
calculating, by the processor, a magnitude of the reflection peak; and
wherein liveness is determined as a function of the calculated magnitude of the reflection peak.
6. The method of claim 5 , wherein the step of determining liveness further comprises:
calculating, by the processor, a liveness score as a function of the magnitude of the reflection peak;
determining, by the processor, that the calculated liveness score exceeds a prescribed threshold.
7. The method of claim 1 , wherein the step of detecting a reflection characteristic further comprises:
measuring the reflection characteristic, wherein the reflection characteristic is one or more of:
a size of the reflection;
a location of the reflection;
a shape of the reflection; and
a magnitude (intensity) of the reflection at one or more portions thereof.
8. The method of claim 7 , wherein the step of determining liveness further comprises one or more of:
determining that the size of the reflection matches a prescribed size;
determining that the location of the reflection corresponds to a location of a pupil of the user;
determining that the shape of the reflection corresponds to a prescribed shape; and
determining that the reflection exhibits a reflection peak having at least a prescribed magnitude.
9. The method of claim 1 , further comprising:
processing, by the processor, at least the first image and the second image using a filter, wherein the filter comprises a band-pass filter applied by the processor to remove reflections and noise present in respective images.
10. The method of claim 1 , wherein the step of detecting the eye in at least the first and the second images comprises:
processing, by the processor, a respective image using a face and or eye finder to identify the location of one or more eyes within the respective image; and
determine, by the processor based on the identified location of the one or more eyes in the at least the first and the second images, that the one or more eyes are positionally stable.
11. The method of claim 1 , further comprising: facilitating, by the processor based on the determination that the imagery depicts a live user, the user's access to an access controlled environment.
12. The method of claim 1 , wherein the step of aligning at least the first and second image is performed, by the processor, based on the orientation of the mobile device during the capture of the images as determined from an onboard position sensor on the mobile device and in communication with the processor.