US 12,111,889 B1
Automated and periodic updating of item images data store
Dilip Kumar, Seattle, WA (US); Jon Robert Ducrou, Seattle, WA (US); Joseph Xavier, Seattle, WA (US); Ramanathan Palaniappan, Issaquah, WA (US); Michel Leonard Goldstein, Seattle, WA (US); and Michael Lee Brundage, Kirkland, WA (US)
Assigned to Amazon Technologies, Inc., Seattle, WA (US)
Filed by Amazon Technologies, Inc., Seattle, WA (US)
Filed on Jun. 17, 2021, as Appl. No. 17/350,402.
Application 17/350,402 is a continuation of application No. 16/415,390, filed on May 17, 2019, granted, now 11,042,787.
Application 16/415,390 is a continuation of application No. 13/929,763, filed on Jun. 27, 2013, granted, now 10,296,814, issued on May 21, 2019.
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 18/24 (2023.01); G06V 10/75 (2022.01)
CPC G06F 18/24 (2023.01) [G06V 10/751 (2022.01)] 16 Claims
OG exemplary drawing
 
1. A computing system, comprising:
one or more processors; and
a memory storing program instructions that, when executed by the one or more processors, cause the one or more processors to at least:
process a first image of an item to determine at least:
a first plurality of features of the item; and
a first arrangement of the first plurality of features in the first image;
determine, based at least in part on a first comparison of the first arrangement of the first plurality of features and stored item image information, a first correlation score indicative of a first similarity between the first arrangement of the first plurality of features and the stored item image information;
process a second image of the item to determine at least:
a second plurality of features of the item; and
a second arrangement of the second plurality of features in the second image;
determine, based at least in part on a second comparison of the second arrangement of the second plurality of features and the stored item image information, a second correlation score indicative of a second similarity between the second arrangement of the second plurality of features and the stored item image information;
determine that the first correlation score does not exceed a threshold;
determine that the second correlation score does not exceed the threshold;
determine, based at least in part on both the first correlation score and the second correlation score collectively, an identity of the item, wherein the identity of the item is associated with the stored item image information; and
based at least in part on of the determination that the first correlation score does not exceed the threshold, store at least one of the first image, a first item image information that includes the first plurality of features and the first arrangement of features, or an association between the item and the first item image information, such that a data set that includes the stored item image information is increased to include at least one of the first image, the first item image information, or the association such that when the item is later imaged for identification by the computing system, the ability of the computing system to identify the item based on the stored item image information is improved.