Image Recognition System and Recognition Method Thereof and Program

• US 20090190834A1
• Filed: 03/24/2009
• Published: 07/30/2009
• Est. Priority Date: 02/27/2002
• Status: Active Grant

• Current Assignee: NEC Corporation
• Original Assignee: NEC Corporation
• Inventors: INOUE, Akira
• Granted Patent: US 8,027,522 B2
• Time in Patent Office: Days
• US Class Current: 382/181
• CPC Class Codes: G06F 18/213 Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
• CPC Class Codes: G06V 10/507 Summing image-intensity values; Histogram projection analysis
• CPC Class Codes: G06V 10/7715 Feature extraction, e.g. by transforming the feature space, e.g. multi-dimensional scaling [MDS]; Mappings, e.g. subspace methods
• CPC Class Codes: G06V 40/16 Human faces, e.g. facial parts, sketches or expressions

Abstract

A task is to correctly classify an input image regardless of a fluctuation in illumination and a state of occlusion of the input image.

Input image sub-region extraction means 2 extracts a sub-region of the input image. Inter-pattern distance calculation means 3 calculates an inter-pattern distance between this sub-region and a sub-region of a registration image pre-filed in dictionary filing means 5 for each sub-region. Region distance value integration means 10 integrates the inter-pattern distances obtained for each sub-region. This is conducted for the registration image of each category. Identification means 4 finds a minimum value out of its integrated inter-pattern distances, and in the event that its minimum value is smaller than a threshold, outputs a category having its minimum distance as a recognition result.

Claims

1. An image recognition system comprising:

fluctuation image generation means for modifying a registration image into a plurality of registration images, each of the plurality of registration images differing in visualization due to a variation in posture and a variation in illumination; and

identification means for identifying said input image based on a plurality of said registration images.

2. The image recognition system as set forth in claim 1,

wherein said identification means identifies said input image by measuring distances between said input image and a subspace of said registration images.

3. An image recognition system comprising;

a first fluctuation image generation means for modifying a registration image into a plurality of registration images, each differing in visualization due to a variation in posture or a variation in illumination;

a second fluctuation image generation means for modifying an input image into a plurality of input images, each differing in visualization due to a variation in posture and a variation in illumination;

inter-subspace distance calculation means for calculating an inter-subspace distance between input images, and said registration images; and

identification means for identifying said input image based on said inter-subspace distance.

4. The image recognition system as set forth in claim 3,

wherein said inter-subspace distance calculation means calculates the inter-subspace distance between a subspace formed by vectors that are generated from said registration images, and a subspace formed by vectors that are generated from said input images.

5. An image recognition method comprising:

using a computer to carry out the steps of;

modifying a registration image into a plurality of registration images, each of the plurality of registration images differing in visualization due to a variation in posture and a variation in illumination; and

identifying said input image based on a plurality of said registration images.

6. The image recognition method as set forth in claim 5,

wherein said identifying of said input image comprises identifying said input image by measuring distances between said input image and a subspace of said registration images.

7. An image recognition method comprising:

using a computer to carry out the steps of;

modifying a registration image into a plurality of registration images, each differing in visualization due to a variation in posture or a variation in illumination;

modifying an input image into a plurality of input images, each differing in visualization due to a variation in posture and a variation in illumination;

calculating an inter-subspace distance between input images, and said registration images; and

identifying said input image based on said inter-subspace distance.

8. The image recognition method as set forth in claim 7,

wherein said calculating of said inter-subspace distance comprises calculating the inter-subspace distance between a subspace formed by vectors that are generated from said registration images, and a subspace formed by vectors that are generated from said input images.

9. A computer-readable storage medium storing a program for executing an image recognition method, the method comprising:

modifying a registration image into a plurality of registration images, each of the plurality of registration images differing in visualization due to a variation in posture and a variation in illumination; and

identifying said input image based on a plurality of said registration images.

10. The computer-readable storage medium as set forth in claim 9,

wherein said identifying of said input image comprises identifying said input image by measuring distances between said input image and a subspace of said registration images.

11. A computer-readable storage medium storing a program for executing an image recognition method, the method comprising:

modifying a registration image into a plurality of registration images, each differing in visualization due to a variation in posture or a variation in illumination;

modifying an input image into a plurality of input images, each differing in visualization due to a variation in posture and a variation in illumination;

calculating an inter-subspace distance between input images, and said registration images; and

identifying said input image based on said inter-subspace distance.

12. The computer-readable storage medium as set forth in claim 11,

wherein said calculating of said inter-subspace distance comprises calculating the inter-subspace distance between a subspace formed by vectors that are generated from said registration images, and a subspace formed by vectors that are generated from said input images.