COMMODITY RECOGNITION APPARATUS

• US 20200134302A1
• Filed: 12/24/2019
• Published: 04/30/2020
• Est. Priority Date: 01/16/2017
• Status: Active Grant

• Current Assignee: Toshiba Tec Corporation (Toshiba Corporation)
• Original Assignee: Toshiba Tec Corporation (Toshiba Corporation)
• Inventors: TAKENO, Yuishi
• Granted Patent: US 11,216,657 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 3/017 Gesture based interaction, e.g. based on a set of recognized hand gestures interaction based on gestures traced on a digitiser G06F3/04883
• CPC Class Codes: G06V 10/255 Detecting or recognising potential candidate objects based on visual cues, e.g. shapes
• CPC Class Codes: G06V 20/68 Food, e.g. fruit or vegetables
• CPC Class Codes: G06V 40/10 Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
• CPC Class Codes: G06V 40/23 Recognition of whole body movements, e.g. for sport training

Abstract

According to an embodiment, a commodity recognition apparatus includes a first camera configured to image a commodity, a posture sensor configured to acquire information indicating a posture of an operator, and a processor configured to acquire the image of the commodity from the first camera, execute commodity recognition processing on the image of the commodity to identify possible matches to previously registered commodity identities upon determining that the posture of the operator satisfies a specified condition according to information from the posture sensor, cause a plurality of commodity candidates are identified as possible matches in the commodity recognition processing, to be displayed on a display screen, and wait for an operator selection of one commodity candidate from the plurality of commodity candidates displayed on the display screen.

Claims

1. A commodity recognition apparatus comprising:

a display;

a first camera configured to image a commodity;

a posture sensor configured to detect a posture of an operator holding the commodity over a reading window; and

a processor configured to

acquire, from the first camera, the image of the commodity that is held over the reading window,

upon detecting that the posture of the operator is in an upright state, execute commodity recognition processing on the image of the commodity to identify one or more commodity candidates, and

control the display to display the identified commodity candidates and then wait for an input that selects one of the commodity candidates.

2. The commodity recognition apparatus according to claim 1, wherein

the processor executes the commodity recognition processing by performing object recognition using a dictionary file.

3. The commodity recognition apparatus according to claim 2, further comprising:

a storage device that stores the dictionary file.

4. The commodity recognition apparatus according to claim 1, wherein

the posture sensor detects that the posture of the operator is in an upright state when the head of the operator is located within a predetermined range.

5. The commodity recognition apparatus according to claim 1, wherein

the posture sensor detects that the posture of the operator is in an upright state when the face of the operator is facing towards the first camera.

6. The commodity recognition apparatus according to claim 1, wherein

the posture sensor is a second camera.

7. The commodity recognition apparatus according to claim 1, wherein

the first camera is also configured as the posture sensor.

8. A commodity recognition apparatus comprising:

a display;

a first camera configured to image a commodity;

a posture sensor configured to detect a posture of an operator holding the commodity over a reading window; and

a processor configured to

acquire, from the first camera, the image of the commodity that is held over the reading window,

upon detecting that the posture of the operator is in an upright state, execute commodity recognition processing on the image of the commodity to identify one or more commodity candidates,

control the display to display the identified commodity candidates and then wait for an input that selects one of the commodity candidates, and

during the waiting, upon detecting that the posture of the operator is not in an upright state,

control the display not to display the identified commodity candidates,

acquire another image of the commodity from the first camera, and

execute the commodity recognition processing on said another image of the commodity.

9. The commodity recognition apparatus according to claim 8, wherein

the processor executes the commodity recognition processing by performing object recognition using a dictionary file.

10. The commodity recognition apparatus according to claim 9, further comprising:

a storage device that stores the dictionary file.

11. The commodity recognition apparatus according to claim 8, wherein

the posture sensor detects that the posture of the operator is in an upright state when the head of the operator is located within a predetermined range.

12. The commodity recognition apparatus according to claim 8, wherein

the posture sensor detects that the posture of the operator is in an upright state when the face of the operator is facing towards the first camera.

13. The commodity recognition apparatus according to claim 8, wherein

the posture sensor is a second camera.

14. The commodity recognition apparatus according to claim 8, wherein

the first camera is also configured as the posture sensor.

15. A method for commodity recognition, the method comprising:

acquiring an image of a commodity that is held by an operator over a reading window;

detecting a posture of the operator holding the commodity over the reading window;

upon detecting that the posture of the operator is in an upright state, executing commodity recognition processing on the image of the commodity to identify one or more commodity candidates; and

displaying the identified commodity candidates and then waiting for an input that selects one of the commodity candidates.

16. The method according to claim 15, wherein

executing commodity recognition processing includes performing object recognition using a dictionary file.

17. The method according to claim 16, further comprising:

storing the dictionary file in a storage device.

18. The method according to claim 15, wherein

the posture of the operator that is in an upright state is detected when the head of the operator is located within a predetermined range.

19. The method according to claim 15, wherein

the posture of the operator that is in an upright state is detected when the face of the operator is facing towards the first camera.

20. The method according to claim 15, wherein

the image of the commodity and the first posture information are acquired by a camera.