IP Library Granted Patent US 9,292,748
Granted Patent B2
US 9,292,748 · App. 14/165,883 · Granted Mar 22, 2016

Information processing apparatus and information processing method

Inventors: Yuta Sasaki (Shizuoka-ken, JP); Hitoshi Iizaka (Shizuoka-ken, JP)
Assignee: Toshiba Tec Kabushiki Kaisha
G06K9/00671G06K2209/17
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 9,292,748
App. No.
14/165,883
Granted
Mar 22, 2016
Kind
B2
Abstract

An information processing apparatus comprises a storage module configured to store feature amounts of standard commodities; an image capturing module configured to photograph a commodity to capture an image of the commodity; an extraction module configured to extract feature amount of the commodity from the image captured by the image capturing module; a calculation module configured to calculate a similarity degree by comparing the feature amount of a standard commodity which is determined as a recognition target in setting information in which a standard commodity serving as a recognition target is set within the standard commodities stored in the storage module with the feature amount of the commodity extracted by the extraction module; and a recognition module configured to recognize a standard commodity of which the similarity degree calculated by the calculation module is greater than a threshold value as a candidate of the commodity.

Claims (36)

1. An information processing apparatus, comprising:

a memory storing therein feature amounts of standard commodities; and

a processor coupled to the memory, the processor configured to:

photograph a commodity to capture an image of the commodity;

extract feature amount of the commodity from the captured image;

calculate a similarity degree by comparing the feature amount of a standard commodity which is determined as a recognition target in setting information in which the standard commodity serving as a recognition target is set within the plurality of standard commodities with the feature amount of the extracted commodity; and

recognize a standard commodity of which the calculated similarity is greater than a threshold value as a candidate of the commodity.

2. The information processing apparatus according to claim 1 , wherein the processor is configured to:

set a commodity to be or not to be a recognition target in the setting information.

3. The information processing apparatus according to claim 2 , wherein the processor is configured to:

record a standard commodity which is incorrectly recognized as history information; and

set, based on the history information, a standard commodity of which the recognition precision is smaller than the threshold value to be a commodity excluded from the recognition target.

4. The information processing apparatus according to claim 3 , wherein the processor is configured to:

indicate a standard commodity recognized as a candidate in a selectable manner;

determine the selected standard commodity as the commodity; and

record, if a standard commodity is selected from standard commodities other than the indicated standard commodities, the selected standard commodity in the history information as an incorrect recognition.

5. The information processing apparatus according to claim 2 , wherein the processor is configured to:

detect a standard commodity of which the quantity of stock is zero, and set the detected standard commodity to be excluded from the recognition target in the setting information.

6. An information processing method, comprising:

a processor to execute the following acts:

storing feature amounts of a plurality of standard commodities;

photographing a commodity to capture an image of the commodity;

extracting feature amount of the commodity from the captured image;

calculating a similarity degree by comparing the feature amount of a standard commodity which is determined as a recognition target in setting information in which a standard commodity serving as a recognition target is set within the plurality of standard commodities with the feature amount of the extracted commodity; and

recognizing a standard commodity of which the calculated similarity degree is greater than a threshold value as a candidate of the commodity.

7. The information processing method according to claim 6 , further comprising:

setting a commodity to be or not to be a recognition target in the setting information.

8. The information processing method according to claim 7 , further comprising:

recording a standard commodity which is incorrectly recognized in the recognition processing as history information; wherein

a standard commodity of which the recognition precision is smaller than a threshold value is set to be a commodity excluded from the recognition target based on the history information.

9. The information processing method according to claim 8 , further comprising:

indicating a standard commodity recognized as a candidate in a selectable manner;

determining the selected standard commodity as the commodity; and

recording, if a standard commodity is selected from standard commodities other than the indicated standard commodities, the selected standard commodity in the history information as an incorrect recognition.

10. The information processing method according to claim 7 , further comprising:

detecting a standard commodity of which the quantity of stock is zero, and setting the detected standard commodity to be excluded from the recognition target in the setting information.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 28, 2014
From: SASAKI, YUTA; IIZAKA, HITOSHI
To: TOSHIBA TEC KABUSHIKI KAISHA
Reel/Frame 032060/0877 →
Priority Claims (1)
JP 2013-022685 · Feb 7, 2013 · national
Continuity (1)
Related Publication 20140219512A1 · Aug 7, 2014