US 12,299,949 B1
Utilizing sensor data for automated user identification
Zheng Tang, Redmond, WA (US); Prithviraj Banerjee, Redmond, WA (US); Manoj Aggarwal, Seattle, WA (US); and Gerard Guy Medioni, Los Angeles, CA (US)
Assigned to Amazon Technologies, Inc., Seattle, WA (US)
Filed by Amazon Technologies, Inc., Seattle, WA (US)
Filed on May 26, 2023, as Appl. No. 18/202,508.
Application 18/202,508 is a continuation of application No. 17/209,845, filed on Mar. 23, 2021, granted, now 11,663,805.
This patent is subject to a terminal disclaimer.
Int. Cl. G06V 10/25 (2022.01); G06F 18/21 (2023.01); G06F 18/22 (2023.01); G06V 40/12 (2022.01)
CPC G06V 10/25 (2022.01) [G06F 18/217 (2023.01); G06F 18/22 (2023.01); G06V 40/1335 (2022.01); G06V 40/1347 (2022.01); G06V 40/1365 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A system comprising:
one or more processors; and
one or more computer-readable media storing computer-executable instructions that, when executed, cause the one or more processors to perform acts comprising:
receiving first image data;
inputting the first image data into a trained model to determine first coordinates associated with a first portion of interest of the first image data, the trained model configured to identify one or more visually salient portions of user palms;
determining first feature data based at least in part on one or more pixel values associated with the first coordinates;
inputting second image data into the trained model to determine second coordinates associated with a second portion of interest of second image data, the second image data representing a palm of a user;
determining second feature data based at least in part on one or more pixel values associated with the second coordinates;
determining that the second coordinates are within a threshold distance of the first coordinates;
generating data indicating a similarity between the first feature data and the second feature data at least partly in response to determining that the second coordinates are within the threshold distance of the first coordinates; and
determining, using the data, that the first image data represents the palm of the user.