US 11,704,887 B2
System, method, apparatus, and computer program product for utilizing machine learning to process an image of a mobile device to determine a mobile device integrity status
Stuart Saunders, Lakewood, OH (US); Anthony Coble, New York, NY (US); Nathan Breitsch, New York, NY (US); and Mircea Ionescu, Wooster, OH (US)
Assigned to ASSURANT, INC., New York, NY (US)
Filed by Assurant, Inc., New York, NY (US)
Filed on Sep. 16, 2020, as Appl. No. 17/22,322.
Claims priority of provisional application 62/900,775, filed on Sep. 16, 2019.
Prior Publication US 2021/0081712 A1, Mar. 18, 2021
Int. Cl. G06N 3/08 (2023.01); G06T 15/30 (2011.01); G06T 15/40 (2011.01); G06V 10/764 (2022.01); G06V 10/24 (2022.01); G06V 10/10 (2022.01); G06F 18/214 (2023.01)
CPC G06V 10/17 (2022.01) [G06F 18/214 (2023.01); G06N 3/08 (2013.01); G06T 15/30 (2013.01); G06T 15/40 (2013.01); G06V 10/24 (2022.01); G06V 10/764 (2022.01)] 38 Claims
OG exemplary drawing
 
1. A method comprising:
receiving a device integrity verification request associated with a mobile device;
receiving mobile device identifying data objects comprising information describing the mobile device;
causing display on the mobile device of a prompt to capture at least one image of the mobile device using one or more image sensors of the mobile device and a reflective surface;
receiving the at least one image captured by the one or more image sensors mobile device;
with at least one trained model, processing the at least one image to determine a mobile device integrity status by determining whether there is at least one of: one or more concave occlusions in the at least one image, or one or more corners blocked in the at least one image, by performing:
generating a mobile device mask comprising a reduced number of colors relative to the at least one image;
extracting a polygonal subregion P of the mobile device mask;
determining a convex hull of P; and
utilizing the convex hull to determine whether there is at least one of (a) one or more concave occlusions in the at least one image, or (b) one or more corners blocked in the at least one image; and
in an instance it is determined there is at least one of one or more concave occlusions in the at least one image, or one or more corners blocked in the at least one image, causing display on the mobile device of a prompt to capture images without occlusions.