CPC G01N 21/8851 (2013.01) [G01N 21/95 (2013.01); G06N 3/045 (2023.01); G06N 3/08 (2013.01); G06N 3/084 (2013.01); G06T 7/0004 (2013.01); G06T 7/001 (2013.01); G06T 7/13 (2017.01); G06T 7/80 (2017.01); G06V 10/42 (2022.01); H04N 7/18 (2013.01); G01N 2021/8854 (2013.01); G01N 2021/8887 (2013.01); G01N 2021/8893 (2013.01); G01N 2021/9513 (2013.01); G01N 21/958 (2013.01); G01N 2201/0221 (2013.01); G06Q 10/30 (2013.01); G06T 7/0002 (2013.01); G06T 2207/10024 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30121 (2013.01); G06T 2207/30244 (2013.01)] | 20 Claims |
1. A system comprising:
a mobile device, the device comprising:
a processor in communication with a memory of the mobile device;
a user interface in communication with the processor, the user interface including a touch-sensitive display and a data entry interface; and
a communications module in communication with the processor and configured to provide a communications interface to a host server, the host server including a server processor communicatively connected to a database, a server communications interface, a server user interface, and a server memory;
wherein the memory of the mobile device includes instructions that when executed by the processor cause the mobile device to perform the steps of:
prompting a user of the mobile device to place the mobile device so that a display section of the mobile device faces a reflective surface of a mirror;
performing a tracking calibration function to adjust the mobile device position and display settings for optimal image capture;
modifying a brightness setting and a camera sensitivity setting of the mobile device to optimize image capture; and
determining that the mobile device is in an acceptable orientation with respect to the mirror, and thereupon:
capturing an image of the mobile device as reflected from the mirror; and
formatting the captured image for transmission to the server for defect analysis;
wherein the server memory includes instructions that when executed by the server processor cause the server to perform the steps of:
receiving the formatted image from the server communications interface;
extracting, from the received image, a subimage corresponding to a screen of the mobile device;
transforming the perspective of the subimage into a rectangular aspect;
resampling the transformed subimage to a predetermined input image data configuration;
presenting the resampled transformed subimage to a pre-trained neural network to identify one or more device defects; and
obtaining from the neural network an indication of a device defect that corresponds to the screen of the mobile device;
wherein obtaining from the neural network an indication of a defect further comprises obtaining, from the neural network, an indicia, created through class activation mapping functions, showing a portion of the screen of the mobile device that activates a defective class in the pre-trained neural network.
|