Abstract: A method of automatically producing a labeled dataset for training a supervised Machine Learning (ML) model to identify items purchased in a store. The method comprising receiving images captured by imaging sensor(s) deployed to monitor an interior space of a store in which a plurality of items are offered for sale, detecting items picked up by customers tracked in the store based on analysis of the images, detecting the picked up items while checked out for the tracked customers at a POS comprising a POS reader configured to read an identifier of each checked out item, correlating between the detected picked up items and respective identifiers received from the POS reader according to timestamps of the identifiers read events, labeling each image depicting a detected item with the respective identifier and outputting a labeled dataset comprising a plurality of labeled images.

Abstract: A method of automatically producing a labeled dataset for training a supervised Machine Learning (ML) model to identify items purchased in a store. The method comprising receiving images captured by imaging sensor(s) deployed to monitor an interior space of a store in which a plurality of items are offered for sale, detecting items picked up by customers tracked in the store based on analysis of the images, detecting the picked up items while checked out for the tracked customers at a POS comprising a POS reader configured to read an identifier of each checked out item, correlating between the detected picked up items and respective identifiers received from the POS reader according to timestamps of the identifiers read events, labeling each image depicting a detected item with the respective identifier and outputting a labeled dataset comprising a plurality of labeled images.

Abstract: A method of automatically producing a labeled dataset for training a supervised Machine Learning (ML) model to identify items purchased in a store. The method comprising receiving images captured by imaging sensor(s) deployed to monitor an interior space of a store in which a plurality of items are offered for sale, detecting items picked up by customers tracked in the store based on analysis of the images, detecting the picked up items while checked out for the tracked customers at a POS comprising a POS reader configured to read an identifier of each checked out item, correlating between the detected picked up items and respective identifiers received from the POS reader according to timestamps of the identifiers read events, labeling each image depicting a detected item with the respective identifier and outputting a labeled dataset comprising a plurality of labeled images.