End user training for computer vision system
Embodiments herein describe providing feedback to a shopper at a POS system using a computer vision system. Many items at a store may lack barcodes or other identifying marks such as produce. The shopper may have to perform an action to identify the item to the POS system. The computer vision system can double check the identify provided by the shopper to reduce mistakes and deter nefarious actors. If the computer vision system cannot independently confirm that the item being purchased matched the identity provided by the shopper, the POS system can display a graphical user interface (GUI) that includes an image of the item captured by the computer vision system along with identification data of the item identified by the shopper. This gives the shopper a chance to correct any mistakes.
1. A method, comprising:
receiving a selected user identification of an item at a point of sale (POS) system;
receiving an identification of the item from a computer vision system;
responsive to determining that the identification of the item by the computer vision system does not match the received selected user identification of the item, generating and displaying a graphical user interface (GUI) at the POS system, the GUI comprising identification data associated with the selected user identification of the item, an actual image of the item captured by the computer vision system, and feedback that the selected user identification of the item does not match the actual image of the item displayed in the GUI,
wherein a first button in the GUI enables the selected user identification to be changed to match the identification of the item by the computer vision system, and a second button in the GUI enables the item corresponding to the selected user identification to be added to a checkout list.
2. The method of claim 1 , further comprising, in response to the second button in the GUI being selected, generating a flag indicating that the computer vision system was unable to confirm the selected user identification of the item.
3. The method of claim 1 , further comprising:
identifying, by the computer vision system and based on the actual image, a plurality of potential items; and
determining, before displaying the GUI, that none of the plurality of potential items identified by the computer vision system match the selected user identification,
wherein the GUI comprises a plurality of buttons each corresponding to a respective one of the plurality of potential items, wherein selecting one of the plurality of buttons changes the selected user identification to match a corresponding item.
4. The method of claim 1 , wherein the identification data is a representative image of the selected user identification of the item and is generated before the item is presented for purchase at the POS system.
5. A point of sale (POS) system, comprising:
a display;
a computer vision system;
a processor; and
memory storing an application which, when executed by the processor performs an operation, the operation comprising:
receiving a selected user identification of an item at the POS system;
receiving an identification of the item from a computer vision system;
upon determining that the identification of the item by the computer vision system does not match the received selected user identification of the item, outputting onto the display a graphical user interface (GUI) comprising identification data of the selected user identification of the item identified, an actual image of the item captured by the computer vision system, and feedback that the selected user identification of the item does not match the actual image of the item displayed in the GUI,
wherein a first button in the GUI enables the selected user identification to be changed to match the identification of the item by the computer vision system, and a second button in the GUI enables the item corresponding to the selected user identification to be added to a checkout list.
6. The system of claim 5 , further comprising, in response to the second button in the GUI being selected, generating a flag indicating that the computer vision system was unable to confirm the selected identification of the item.
7. The system of claim 5 , wherein the operation further comprises:
identifying, by the computer vision system and based on the actual image, a plurality of potential items; and
determining, before displaying the GUI, that none of the plurality of potential items identified by the computer vision system match the selected user identification,
wherein the GUI comprises a plurality of buttons each corresponding to a respective one of the plurality of potential items, wherein selecting one of the plurality of buttons changes the selected user identification to match a corresponding item.
8. A computer-readable storage medium having computer-readable program code embodied therewith, the computer-readable program code executable by one or more computer processors to perform an operation, the operation comprising:
receiving a selected user identification of an item at a point of sale (POS) system;
receiving an identification of the item from a computer vision system;
upon determining that the identification of the item by the computer vision system does not match the received selected user identification of the item, transmitting for display, in a graphical user interface (GUI) at the POS system, identification data of the item, an actual image of the item captured by the computer vision system, and feedback that the selected user identification of the item does not match the actual image of the item displayed in the GUI,
wherein a first button in the GUI enables the selected user identification to be changed to match the identification of the item by the computer vision system, and a second button in the GUI enables the item corresponding to the selected user identification to be added to a checkout list.
9. The computer-readable storage medium of claim 8 , further comprising, in response to the second button in the GUI being selected, generating a flag indicating that the computer vision system was unable to confirm the selected user identification of the item.