US 12,254,709 B2
Using image processing to identify produce
Andrea Bordone Molini, London (GB); Francesco Lupo, London (GB); and Andrea Mirabile, London (GB)
Assigned to Zebra Technologies Corporation, Lincolnshire, IL (US)
Filed by ZEBRA TECHNOLOGIES CORPORATION, Lincolnshire, IL (US)
Filed on Feb. 28, 2022, as Appl. No. 17/683,134.
Prior Publication US 2023/0274560 A1, Aug. 31, 2023
Int. Cl. G06V 20/68 (2022.01); G06Q 20/20 (2012.01); G06V 10/20 (2022.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01)
CPC G06V 20/68 (2022.01) [G06Q 20/208 (2013.01); G06V 10/255 (2022.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A method for identifying produce using image analysis, comprising:
receiving, at a controller, a trigger associated with presence of an item at a product processing zone;
capturing, via an imager having a field of view (FOV) extending at least partially over the product processing zone, an image representing the item;
applying a first convolutional neural network (CNN) to the image to determine a bounding box associated with the item;
determining that the item within the bounding box satisfies an occlusion threshold;
applying a second CNN to the image to determine a query image representation;
receiving, from a database, an indication of one or more candidate items based on the query image representation; and
indicating, via a user interface, the one or more candidate items to a user.