US 11,720,650 B2
Methods and apparatus for training a classification model based on images of non-bagged produce or images of bagged produce generated by a generative model
Christopher Bradley Rodney Sampson, Sydney (AU); Sufyan Asghar, Bavaria (DE); and Rui Dong, Sydney (AU)
Assigned to Tiliter Pty Ltd., Sydney (AU)
Filed by Tiliter Pty Ltd., Sydney (AU)
Filed on Oct. 30, 2020, as Appl. No. 17/85,585.
Prior Publication US 2022/0138488 A1, May 5, 2022
Int. Cl. G06K 9/62 (2022.01); G06F 18/2431 (2023.01); G06N 3/088 (2023.01); G06F 18/214 (2023.01); G06N 3/045 (2023.01)
CPC G06F 18/2431 (2023.01) [G06F 18/214 (2023.01); G06N 3/045 (2023.01); G06N 3/088 (2013.01)] 21 Claims
OG exemplary drawing
 
1. A method, comprising:
receiving a plurality of images of non-bagged produce;
executing a first machine learning model to generate a plurality of images of bagged produce based on the plurality of images of non-bagged produce;
training a second machine learning model based on the plurality of images of bagged produce and the plurality of images of non-bagged produce; and
executing, after the training, the second machine learning model to classify as a bagged produce or a non-bagged produce an image not included in the plurality of images of non-bagged produce and not included in the plurality of images of bagged produce.