IP Library Granted Patent US 9,747,512
Granted Patent B2
US 9,747,512 · App. 14/750,833 · Granted Aug 29, 2017

Article recognition apparatus and image processing method for article recognition apparatus

Inventors: Tetsuya Nobuoka (Sunto Shizuoka, JP); Masaaki Yasunaga (Sunto Shizuoka, JP)
Assignee: Toshiba TEC Kabushiki Kaisha
G06K9/46G06K7/10722G06K9/6215G06Q20/208G06T7/11G06K2009/6213G06T2207/10004
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 9,747,512
App. No.
14/750,833
Granted
Aug 29, 2017
Kind
B2
Abstract

According to one embodiment, an article recognition apparatus includes an image acquisition unit, a recognition unit, a region detection unit, a storage unit, and a determination unit. The recognition unit recognizes each of the articles. The region detection unit determines article region information. The storage unit stores article information including a reference value for the article region information. The determination unit determines that an unrecognized article exists, if the reference value for the article region information of each article which the recognition unit recognized does not match with the article region information.

Claims (39)

1. An article recognition apparatus comprising:

an interface configured to acquire a photographic image of a table on which a plurality of articles to be recognized is disposed;

a database that stores a reference value for each article to be recognized in the plurality of articles; and

a processor configured to detect identification patterns in the photographic image, to recognize each article in the plurality of articles corresponding to one of the detected identification patterns,

to detect image regions occupied by the plurality of articles in the photographic image, to determine article region information from the detected image regions, and

to determine that an unrecognized article is in the plurality articles disposed on the table if the reference values for each article recognized by detection of identification patterns does not match the article region information.

2. The apparatus of claim 1 , wherein the database stores a reference area for the image region of the article as the reference value, and

the processor is configured to detect the image regions of all articles in the photographic image, to determine an area of the detected image regions of all articles, and

to determine that an unrecognized article exists if a total area of the reference areas of each recognized article in the photographic image does not match the area of the detected image regions of all articles in the photographic image.

3. The apparatus of claim 1 , wherein the storage unit database stores a reference area for the image region of the article as the reference value, and

the processor is configured to detect the image region of each individual article recognized in the photographic image, to determine an area of the detected image region of each recognized individual article, and

to determine that an unrecognized article exists in the detected image region of the recognized article, if the area of the detected image region of the recognized article does not match the reference area of the recognized article.

4. The apparatus of claim 3 , further comprising a sensor configured to measure a height of an article in the plurality of articles on the table,

wherein the database stores a reference height for each article in the plurality of articles, and

the processor is configured to determine that an unrecognized article is in the plurality of articles if the height of a recognized article in the plurality of articles that the sensor measures does not match the reference height of the recognized article.

5. An article recognition apparatus comprising:

a first interface image acquisition unit configured to acquire a photographic image of a table on which a plurality of articles to be recognized is disposed;

a database that stores a reference value for each article to be recognized in the plurality of articles;

a processor configured to detect identification patterns in the photographic image, to recognize each article in the plurality of articles corresponding to the detected identification patterns,

to detect image regions occupied by the plurality of articles in the photographic image, to determine article region information from the detected image regions, and

to determine that an unrecognized article, is in the plurality of articles disposed on the table if the reference values for each article recognized by detection of the identification patterns do not match the article region information; and

a second interface through which a distance image depicting distances to the plurality of articles disposed on the table is acquired.

6. The apparatus of claim 5 , wherein the database stores a reference height for each article in the plurality of articles,

the processor is configured to detect the image region for each of the individual articles from the distance image, to determine an article height in the detected image regions, and

to determine that an unrecognized article is in the plurality of articles if the article height in the detected image region does not match the reference height of the recognized article.

7. The apparatus of claim 5 , wherein the database stores a reference area for the image region of the article as the reference value, and

the processor is configured to detect the image regions of all articles from the distance image, to determine an area of the detected image regions of all articles, and

to determine that an unrecognized article is in the plurality of articles, if a total area of the reference areas of each recognized article does not match the area of the detected image regions of all articles.

8. The apparatus of claim 5 , wherein the database is configured to store a reference area for the image region of each article as the reference value,

the processor is configured to detect the image region of each of the individual articles from the distance image, to determine an area of the detected image region of each individual article, and

to determine that an unrecognized article exists in the detected image regions, if the area of the detected image region of each individual article does not match with the reference area of the recognized article.

9. The apparatus of claim 8 , further comprising a sensor configured to measure a height of an article in the plurality of articles on the table,

wherein the database stores a reference height for each article in the plurality of articles, and

the processor is configured to determine that an unrecognized article exists in the image region of a recognized article, if an area of the detected image region of the recognized article does not match the reference area of the recognized article or if a height of the recognized article as measured by the sensor does not match the reference height of the recognized article.

10. An image processing method comprising:

acquiring a photographic image including a plurality of articles disposed on a table;

detecting an identification pattern in the photographic image corresponding to an article in the plurality of articles, and recognizing the article by the detected identification pattern;

detecting image regions occupied by the plurality of articles in the photographic image, and determining article region information for the detected image regions; and

determining that an unrecognized article exists if a reference value for the recognized articles in the plurality of articles does not match the article region information determined for the detected image regions.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 25, 2015
From: NOBUOKA, TETSUYA; YASUNAGA, MASAAKI
To: TOSHIBA TEC KABUSHIKI KAISHA
Reel/Frame 035909/0169 →
Continuity (1)
Related Publication 20160379076A1 · Dec 29, 2016