US 11,756,036 B1
Utilizing sensor data for automated user identification
Manoj Aggarwal, Seattle, WA (US); Prithviraj Banerjee, Redmond, WA (US); Gerard Guy Medioni, Seattle, WA (US); and Brad Musick, Seattle, WA (US)
Assigned to Amazon Technologies, Inc., Seattle, WA (US)
Filed by Amazon Technologies, Inc., Seattle, WA (US)
Filed on Dec. 13, 2019, as Appl. No. 16/714,348.
Int. Cl. G06V 40/12 (2022.01); G06Q 20/40 (2012.01); G06V 10/46 (2022.01); G06V 40/13 (2022.01); G06F 18/2321 (2023.01)
CPC G06Q 20/40145 (2013.01) [G06F 18/2321 (2023.01); G06V 10/462 (2022.01); G06V 40/13 (2022.01); G06V 40/1359 (2022.01); G06V 40/1376 (2022.01)] 18 Claims
OG exemplary drawing
 
1. A system comprising:
one or more processors; and
one or more non-transitory computer-readable media storing computer-executable instructions that, when executed, cause the one or more processors to perform operations comprising:
receiving, from a user-recognition system, a request to verify that a first palm depicted in first image data corresponds to a second palm depicted in second image data;
receiving the first image data depicting the first palm;
receiving the second image data depicting the second palm;
identifying, using the first image data, a first characteristic exhibited in a first portion of the first palm, the first portion being less than an entirety of the first palm;
extracting, from the first image data, first feature data representing the first characteristic exhibited in the first palm;
extracting, from the second image data, second feature data representing the first characteristic exhibited in the second palm;
analyzing, by the system, the first feature data with reference to the second feature data;
calculating, based at least in part on the analyzing the first feature data, a first similarity score representing a measure of similarity between the first characteristic exhibited in the first palm and the first characteristic exhibited in the second palm;
identifying, using the first image data, a second characteristic exhibited in a second portion of the first palm, the second portion being less than an entirety of the first palm;
extracting, from the first image data, third feature data representing the second characteristic exhibited in the first palm;
extracting, from the second image data, fourth feature data representing the second characteristic exhibited in the second palm;
analyzing, by the system, the third feature data with reference to the fourth feature data;
calculating, based at least in part on the analyzing the third feature data, a second similarity score representing a measure of similarity between the second characteristic exhibited in the first palm and the second characteristic exhibited in the second palm;
verifying, based at least in part on the first similarity score and the second similarity score, that the first palm corresponds to the second palm; and
sending, to the user-recognition system, output data verifying that the first palm corresponds to the second palm.