US 12,340,360 B2
Systems and methods for item recognition
Shiyuan Yang, Shanghai (CN); Lin Gao, Syosset, NY (US); Yufeng He, Shanghai (CN); Xiao Zhou, Shanghai (CN); Yilin Huang, Shanghai (CN); Griffin Kelly, Chicago, IL (US); Isabel Tsai, New York, NY (US); and Ahmed Beshry, Queens, NY (US)
Assigned to Maplebear Inc., San Francisco, CA (US)
Filed by Maplebear Inc., San Francisco, CA (US)
Filed on Sep. 22, 2022, as Appl. No. 17/950,310.
Claims priority of application No. 202111110492.6 (CN), filed on Sep. 23, 2021.
Prior Publication US 2023/0087587 A1, Mar. 23, 2023
Int. Cl. G06Q 20/20 (2012.01); B62B 3/14 (2006.01); G07G 1/00 (2006.01)
CPC G06Q 20/208 (2013.01) [B62B 3/14 (2013.01); G07G 1/0045 (2013.01); B62B 2203/50 (2013.01)] 30 Claims
OG exemplary drawing
 
1. A computer vision system for identifying merchandise, comprising:
at least one processor adapted to obtain computer-executable instructions stored on a non-transitory medium that, when executed by the at least one processor, cause the at least one processor to:
receive one or more images of merchandise selected by a shopper from a camera of a user device;
identify, in the one or more images of merchandise selected by a shopper, an identifier affixed to the selected merchandise by:
generating a naïve item category of the selected merchandise; and
localizing a portion of the image containing the identifier based on the naïve item category;
identify, based on the one or more images, an actual item category of the selected merchandise; and
compare the identifier and the actual item category identified in each respective image to identify the merchandise.