Methods, systems, and media for detecting spoofing in mobile authentication

A system for recognizing a class or within-class identity of a 3D object, in a mobile object detection and identity recognition process, the system comprising:

• a mobile device comprising a front-facing camera, a front-facing screen, at least one processor, a memory;
• and a server comprising at least one processor and a memory:
• the mobile device configured to:
• a) capture, via the front-facing camera,
• i) a first image data of the 3D object while displaying, via the front-facing screen, first identification pattern comprising a plurality of first identification pattern regions, wherein at least one of the first identification pattern regions varies from another first identification pattern region in at least one of:
• brightness, position, size, shape, and color over time causing a first variance of lighting effects, wherein the first image data comprises a first set of highlights and shadows on the 3D object over time;
• ii) a second image data of the 3D object while displaying, via the front-facing screen, the second identification pattern after displaying the first identification pattern, wherein the second identification pattern is different from the first identification pattern, the second identification pattern comprising a plurality of second identification pattern regions, wherein at least one of the second identification pattern regions varies from another second identification pattern regions in at least one of brightness, position, size, shape, and color causing a second variance of lighting effects, wherein the second image data comprises a second set of highlights and shadows on the 3D object over time;
• and
• b) transmit the first image data and the second image data to the server;
• the server configured to:
• a) receive the first image data and the second image data from the mobile device;
• b) calculate a difference between the first set of highlights and shadows and the second set of highlights and shadows to determine a current spatial characteristic of the 3D object;
• c) determine the class, or the within-class identity of the 3D object in the mobile object detection and identity recognition process by comparing the current spatial characteristic of the 3D object with a stored reference spatial characteristic of the 3D object;
• and
• d) transmit the class, or the within-class identity to the mobile device.

A method of recognizing a class or within-class identity of a 3D object, in a mobile object detection and identity recognition process, the method comprising:

• a) capturing, via a front-facing camera of a mobile device,
• i) a first image data of the 3D object while displaying, via a front-facing screen of the mobile device, a first identification pattern, the first identification pattern comprising a plurality of first identification pattern regions, wherein at least one of the first identification pattern regions varies from another first identification pattern region in at least one of:
• brightness, position, size, shape, and color over time causing a first variance of lighting effects, wherein the first image data comprises a first set of highlights and shadows on the 3D object over time, and
• ii) a second image data of the 3D object while displaying, via the front-facing screen, the second identification pattern after displaying the first identification pattern, wherein the second identification pattern is different from the first identification pattern, the second identification pattern comprising a plurality of second identification pattern regions, wherein at least one of the second identification pattern regions varies from another second identification pattern regions in at least one of brightness, position, size, shape, and color causing a second variance of lighting effects, wherein the second image data comprises a second set of highlights and shadows on the 3D object over time;
• b) calculating a difference between the first set of highlights and shadows and the second set of highlights and shadows to determine a current spatial characteristic of the 3D object;
• and
• c) determining the class, or the within-class identity of the 3D in the mobile object detection and identity recognition process by comparing the current spatial characteristic of the 3D object with a stored reference spatial characteristic of the 3D object.