Context-aided machine vision
AssigneeNCR Voyix Corporation
InventorsBrent Vance Zucker, Adam Justin Lieberman
Life of this patent
Estimating the term…
Abstract
Various embodiments herein each include at least one of systems, methods, software, and data structures for context-aided machine vision. For example, one method embodiment includes identifying a customer in a shopping area and maintaining an item bin in a computing system of data identifying items the customer has picked up for purchase. This method further includes receiving an image of the customer holding an item and performing item identification processing on the image to identify the item the customer is holding. The item identification processing may be performed based in part on a stored shopping history of the customer indicating items the customer is more likely to purchase. The identified item is then added to the item bin of the customer.
Claims20
A method, comprising:
- receiving an image depicting a customer holding an item;
- obtaining a history for the customer;
- determining an item identifier for the item held by the customer based on the image and the history of the customer;
- and
- adding the item identifier to an item bin associated with the customer.
A method, comprising:
- tracking a customer within a shopping area through images captured of the customer within the shopping area;
- obtaining an item purchase history for the customer;
- and
- adding certain item identifiers for certain items picked up by the customer within the shopping area and placed in a cart of the customer to an item bin based on the images and the item purchase history of the customer until a given image indicates the customer has left the shopping area.
A system, comprising:
- a processor;
- a memory device;
- and
- instructions stored on the memory device that when executed by the processor cause the processor to perform operations comprising:
- performing item identification on a given image to identify an item a customer is holding based at least in part on a customer item purchase history representing a customer likelihood to purchase certain items and not to purchase other items;
- and
- adding a given item identifier for the item to an item bin associated with the customer, wherein the item bin identifying items the customer has picked up for purchase within a shopping area of a store.
Dependencies are inferred from the claim text.