US 12,272,217 B1
Automatic item identification during assisted checkout based on visual features
Abhinav Yarlagadda, Woodinville, WA (US); Enis Dengi, Tempe, AZ (US); Sai Krishna Bashetty, Bellevue, WA (US); Rahul Santhosh Kumar Varma, Tempe, AZ (US); Daniel King, Seattle, MA (US); Kamalesh Kalirathinam, Tempe, AZ (US); and Sri Priyanka Madduluri, Arlington, VA (US)
Assigned to RadiusAI, Inc., Tempe, AZ (US)
Filed by RadiusAI, Inc., Tempe, AZ (US)
Filed on Oct. 4, 2024, as Appl. No. 18/906,813.
Claims priority of provisional application 63/587,874, filed on Oct. 4, 2023.
Int. Cl. G07G 1/00 (2006.01); G06F 16/55 (2019.01); G06V 10/26 (2022.01); G06V 10/75 (2022.01); G06V 10/762 (2022.01); G06V 10/77 (2022.01); G06V 10/82 (2022.01)
CPC G07G 1/0045 (2013.01) [G06F 16/55 (2019.01); G06V 10/26 (2022.01); G06V 10/762 (2022.01); G06V 10/7715 (2022.01); G06V 10/82 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A system for automatically identifying a plurality of items positioned at a point of sale (POS) system based on a plurality of item parameters associated with each item as provided by a plurality of images captured by a plurality of cameras positioned at the POS system, comprising:
at least one processor;
a memory coupled with the at least one processor, the memory including instructions that, when executed by the at least one processor cause the at least one processor to:
extract the plurality of item parameters associated with each item positioned at the POS system from the plurality of images of each item captured by the plurality of cameras positioned at the POS system to map the plurality of item parameters into a corresponding feature vector for each item, wherein the item parameters associated with each item when combined and mapped into the corresponding feature vector for each item are indicative as to an identification of each corresponding item thereby enabling the identification of each corresponding item,
analyze each feature vector associated with each item positioned at the POS system to determine whether the item parameters when combined and mapped into each feature vector associated with each item matches a corresponding stored feature vector stored in an item parameter database, wherein the item parameter identification database stores different combinations of item parameters as mapped into different stored feature vectors with each different stored feature vector associated with a corresponding item thereby identifying each corresponding item based on each different combination of item parameters mapped to each corresponding stored feature vector associated with each corresponding item,
identify each corresponding item positioned at the POS system when each feature vector associated with each item matches a corresponding stored feature vector as stored in the item parameter identification database and fail to identify each corresponding item when each feature vector associated with each item fails to match a corresponding stored feature vector, and
stream each feature vector associated with each item positioned at the POS system that fails to match a corresponding stored feature vector stored in the item parameter identification database thereby enabling the identification of each failed item when each feature vector of each failed item are subsequently identified when positioned at the POS system after the failed match.