US 11,893,786 B1
Scan-free barcode reading
Frank Preiswerk, Brooklyn, NY (US); Timothy Stallman, Groton, MA (US); Michael R. Calder, Westborough, MA (US); and Armon Shariati, Cambridge, MA (US)
Assigned to Amazon Technologies, Inc., Seattle, WA (US)
Filed by Amazon Technologies, Inc., Seattle, WA (US)
Filed on Aug. 17, 2021, as Appl. No. 17/404,519.
Int. Cl. G06V 10/25 (2022.01); G06V 20/10 (2022.01); G06K 7/14 (2006.01); G06F 18/214 (2023.01); G06F 18/25 (2023.01); G06V 10/80 (2022.01); G06V 30/00 (2022.01)
CPC G06V 20/10 (2022.01) [G06F 18/214 (2023.01); G06F 18/253 (2023.01); G06K 7/1413 (2013.01); G06V 10/25 (2022.01); G06V 10/806 (2022.01); G06V 30/00 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A scan-free reader system, comprising
a plurality of image sensors, each disposed in a different location within an environment to create a scanning volume within the environment; and
a computing system coupled to the plurality of image sensors and configured to:
capture, via the plurality of image sensors, a first plurality of images of an object within the scanning volume, wherein the object is moved through the scanning volume (i) as part of a picking operation or a stowing operation and (ii) without an explicit presentation of a structured identifier on the object to at least one of the plurality of image sensors;
generate a second plurality of images corresponding to the first plurality of images, wherein each of the second plurality of images has a lower quality than a respective one of the first plurality of images;
determine, via a machine learning model, a first region of interest of the structured identifier on the object within a first image of the second plurality of images;
identify, based on the first region of interest, a second region of interest of the structured identifier on the object within a first image of the first plurality of images corresponding to the first image of the second plurality of images;
extract an image of the second region of interest within the first image of the first plurality of images; and
decode the structured identifier within the image of the second region of interest to obtain data corresponding to the structured identifier.