US 11,941,581 B2
System and method for classifier training and retrieval from classifier database for large scale product identification
Moshe Meidar, Florida, FL (US); Gidon Moshkovitz, Haifa (IL); Edi Bahous, Haifa (IL); and Itai Winkler, Haifa (IL)
Assigned to TRACXPOINT LLC., Coral Gables, FL (US)
Filed by TRACXPOINT LLC., Coral Gables, FL (US)
Filed on Feb. 9, 2022, as Appl. No. 17/667,590.
Application 17/667,590 is a continuation of application No. 17/267,839, granted, now 11,386,639, previously published as PCT/IL2019/051390, filed on Dec. 19, 2019.
Claims priority of provisional application 62/782,377, filed on Dec. 20, 2018.
Prior Publication US 2022/0165046 A1, May 26, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06K 9/32 (2006.01); B62B 3/14 (2006.01); G06F 18/22 (2023.01); G06F 18/23213 (2023.01); G06F 18/2413 (2023.01); G06K 9/00 (2022.01); G06K 9/62 (2022.01); G06N 3/02 (2006.01); G06N 3/04 (2023.01); G06Q 10/087 (2023.01); G06V 10/70 (2022.01); G06V 20/20 (2022.01); G06V 20/52 (2022.01); G06V 30/194 (2022.01)
CPC G06Q 10/087 (2013.01) [B62B 3/14 (2013.01); G06F 18/22 (2023.01); G06F 18/23213 (2023.01); G06F 18/24147 (2023.01); G06N 3/02 (2013.01); G06N 3/04 (2013.01); G06V 10/87 (2022.01); G06V 20/20 (2022.01); G06V 20/52 (2022.01); G06V 30/194 (2022.01); G06V 2201/09 (2022.01)] 11 Claims
OG exemplary drawing
 
1. A system for automated classification of a product in a shopping cart, the system comprising:
a. a cart having a front wall, a rear wall and two side walls forming an apically open container with a base;
b. a plurality of imaging modules coupled to the cart, adapted to image at least one of: an item inserted into the cart, and an area of interest outside the cart; and
c. a central processing module in communication with the plurality of imaging modules, the central processing module comprising a processor and being in further communication with a non-volatile memory having thereon: a classifiers' database; a product characteristics database; and a processor-readable media comprising a set of executable instruction, configured, when executed to cause the processor to retrieve a set of a plurality of classifiers from the classifier database, wherein each set of classifiers retrieved is configured to identify a single product inserted into the cart, the set of executable instructions is configured, when executed, to cause the processor further to:
i. using the imaging module, capture an image of each inserted product;
ii. preprocess the image of each product inserted to the cart by reducing the number of colors of the product;
iii. extract a predetermined number of features from the image with reduced colors;
iv. identify the features extracted; and
v. using the features extracted as a key, extract a set of relevant classifiers configured to produce a single product recognition.