Object Recognition Apparatus,Computer Readable Medium Storing Object Recognition Program, and Image Retrieval Service Providing Method

• US 20090129683A1
• Filed: 05/09/2007
• Published: 05/21/2009
• Est. Priority Date: 05/10/2006
• Status: Active Grant

• Current Assignee: Nikon Corporation
• Original Assignee: Nikon Corporation
• Inventors: Nitta, Keiichi
• Granted Patent: US 8,379,990 B2
• Time in Patent Office: Days
• US Class Current: 382/227
• CPC Class Codes: G06F 16/58 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
• CPC Class Codes: G06F 18/24323 Tree-organised classifiers
• CPC Class Codes: G06F 18/28 Determining representative reference patterns, e.g. by averaging or distorting; Generating dictionaries
• CPC Class Codes: G06V 10/764 using classification, e.g. of video objects
• CPC Class Codes: G06V 10/772 Determining representative reference patterns, e.g. averaging or distorting patterns; Generating dictionaries
• CPC Class Codes: G06V 20/10 Terrestrial scenes scenes under surveillance with static cameras G06V20/52; scenes perceived from the exterior of a vehicle G06V20/56; scenes perceived from the interior of a vehicle G06V20/59
• CPC Class Codes: G06V 30/242 Division of the character sequences into groups prior to recognition; Selection of dictionaries

Abstract

An object recognition apparatus includes an image input unit capturing image data, an object dictionary unit storing conditions to specify a type of an object, and a processor collating the image data with the conditions and specifying the type of the object imaged in the image data, in which the object dictionary unit classifies the conditions into hierarchies and stores the classified conditions, and the processor performs collation while narrowing down object conditions positioned in lower hierarchies based on a collation result of object conditions positioned in upper hierarchies.

Claims

1. An object recognition apparatus comprising:

an image input unit capturing image data;

an object dictionary unit storing conditions to specify a type of an object; and

a processor collating the image data with the conditions and specifying the type of the object imaged in the image data, wherein

the object dictionary unit classifies the conditions into hierarchies and stores the classified conditions, and

the processor performs collation while narrowing down object conditions positioned in lower hierarchies based on a collation result of object conditions positioned in upper hierarchies.

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

the processor makes predetermined keyword information related to the recognized type of the object correspond to the image data and records the predetermined keyword information, and

performs image retrieval by collating an input keyword with the keyword information corresponding to the image data.

3. The object recognition apparatus according to claim 1, wherein

the object dictionary unit has a function to perform additional registrations of an object type Kd and an object condition Cd, and

the processor finds an object type Ku, which includes the object type Kd, in the upper hierarchy according to the additional registration by the object dictionary unit, and additionally performs collation of the image data, in which the object type Ku has been detected, with the object condition Cd.

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

the object dictionary unit has a function to manage version information of the conditions, and

the processor makes the version information of the conditions used to specify the type of the object correspond to the image data and records the version information.

5. An object recognition apparatus, comprising:

an image input unit capturing image data;

an object dictionary unit storing conditions to specify a type of an object in accordance with a hierarchical structure of the type of the object; and

a processor collating the image data with the conditions and specifying the type of the object imaged in the image data, wherein

the object dictionary unit has a function to perform additional registration of an object type Ku as a hierarchy upper than that of a registered object type Kd, and

the processor assumes the image data in which the object type Kd has been detected as the image data in which the object type Ku has been detected and classifies the image data in which the object type Kd has been detected, according to the additional registration.

6. The object recognition apparatus according to claim 5, wherein

the object dictionary unit has a function to perform additional registration of the plurality of detected types of the objects as the object type Ku in upper hierarchies, and

the processor finds a sum of sets of the image data in which the plurality of types of the objects have been detected, assumes the image data in which the plurality of types of the objects have been detected as the image data in which the object type Ku has been detected, and classifies the image data in which the plurality of types of the objects have been detected, according to the additional registration.

7. The object recognition apparatus according to claim 5, wherein

the object dictionary unit has a function to manage version information of the conditions, and

the processor makes the version information after the additional registration correspond to the image data which is assumed to be the object type Ku and records the version information.

8. A computer readable medium storing an object recognition program which causes a computer to function to perform an object recognition process, comprising:

capturing image data;

classifying conditions to specify a type of an object into hierarchies and storing the classified conditions; and

finding the type of the object imaged in the image data by narrowing down object conditions positioned in lower hierarchies based on a result of collating the image data with object conditions positioned in upper hierarchies of the classified conditions.

9. An image retrieval service providing method for causing a computer to perform an image retrieval service, comprising:

classifying conditions to specify a type of an object into hierarchies and storing the classified conditions;

finding the type of the object imaged in the image data upon collating the image data with the conditions sequentially in accordance with the hierarchies;

making predetermined keyword information related to the recognized type of the object correspond to the image data and recording the predetermined keyword information; and

performing image retrieval and collating an input keyword with the keyword information corresponding to the image data.

10. An image retrieval service providing method for causing a computer to perform an image retrieval service, comprising:

classifying conditions to specify a type of an object into hierarchies and storing the classified conditions;

finding the type of the object imaged in the image data upon collating the image data with the conditions sequentially in accordance with the hierarchies;

assuming the image data in which an object type Kd has been detected to be the image data in which an object type Ku has been detected, after accepting additional registration of the object type Ku as a hierarchy upper than that of the registered object type Kd;

making predetermined keyword information related to the recognized type of the object correspond to the image data and recording the predetermined keyword information; and

performing image retrieval and collating an input keyword with the keyword information corresponding to the image data.

11. An image retrieval service providing method for causing a computer to perform an image retrieval service, comprising:

classifying conditions to specify a type of an object into hierarchies and storing the classical conditions;

finding the type of the object imaged in the image data by narrowing down object conditions positioned in lower hierarchies based on a result of collating the image data with object conditions positioned in upper hierarchies of the classified conditions; and

finding an object type Ku, which includes an object type Kd, in the upper hierarchy, and additionally performing collation of the image data, in which the object type Ku has been detected, with the object condition Cd, after accepting additional registrations of the object type Kd and the object condition Cd.